Tuesday, May 6
8:45 AM - 9:20 AM
Opening Ceremony (Room Cavaniglia)
9:20 AM - 9:40 AM
State of Society Presentation
9:40 AM - 10:30 AM
Awards Ceremony
10:30 AM - 11:00 AM
Coffee break
11:00 AM - 1:00 PM
SS1: Signal Processing for Big Data
Room: Cavaniglia
Chair: Nikolaos D Sidiropoulos (University of Minnesota, USA)
- 11:00 A Parallel Algorithm for Big Tensor Decomposition Using Randomly Compressed Cubes (PARACOMP)
- 11:20 Fast and Robust Bootstrap method for testing hypotheses in the ICA model
- 11:40 Computing Persistent Features in Big Data: A Distributed Dimension Reduction Approach
- 12:00 Online Dictionary Learning from Big Data Using Accelerated Stochastic Approximation Algorithms
- 12:20 Metric learning with rank and sparsity constraints
- 12:40 Distributed Large-Scale Tensor Decomposition
SPTM-L1: Sampling Theory and Methods I
Room: Basilica
Chairs: Helmut Boelcskei (ETH, Switzerland), Pier Luigi Dragotti (Imperial College London, United Kingdom)
- 11:00 Spatio-Temporal Sampling and Reconstruction of Diffusion Fields induced by Point Sources
- 11:20 Super-resolution from short-time Fourier transform measurements
- 11:40 Non-uniform Sampling for Compressive Cyclic Spectrum Reconstruction
- 12:00 A Phase Retrieval Method for Signals in Modulation-Invariant Spaces
- 12:20 Fitting instead of Annihilation: improved recovery of noisy FRI signals
- 12:40 No-Go Theorem for Sampling-Based Signal Processing
SAM-L1: Radar Array Processing
Room: Polveriera
Chairs: Maria S. Greco (University of Pisa, Italy), Peter Willett (University of Connecticut, USA)
- 11:00 Enhanced Radar Detection and Range Estimation via Oversampled Data
- 11:20 Robust Estimation of the Clutter Subspace for a Low Rank Heterogeneous Noise under High Clutter to Noise Ratio Assumption
- 11:40 A Max-Min Design of Transmit Sequence and Receive Filter
- 12:00 Multichannel Radar Backscatter Communication and Localization
- 12:20 Compressed Spectrum Sensing in Cognitive Radar Systems
- 12:40 Angular resolution limit of two closely-spaced point sources based on information theoretic criteria
SLTC-L1: Speaker diarization
Room: Scherma
Chairs: Hagai Aronowitz (IBM Research - Haifa, Israel), Andreas Stolcke (Microsoft & ICSI, USA)
- 11:00 Variational Bayes Based I-vector for Speaker Diarization of Telephone Conversations
- 11:20 Information Bottleneck based Speaker Diarization of Meetings using Non-speech as Side Information
- 11:40 Improving Speaker Diarization using social role information
- 12:00 Bayesian Analysis of Similarity Matrices for Speaker Diarization
- 12:20 Filterbank Slope based Features for Speaker Diarization
- 12:40 A Conditional Random Field approach for Audio-Visual people diarization
SLTC-L2: Spoken Language Understanding I
Room: Teatrino
Chairs: Pascale Fung (University of Science & Technology (HKUST), Hong Kong), Fabrice Lefevre (University of Avignon, France)
- 11:00 Classification of clean and noisy bilingual movie audio for speech-to-speech translation corpora design
- 11:20 Improving Dialogue Classification using a Topic Space Representation and a Gaussian Classifier based on the Decision Rule
- 11:40 Wikipedia-based Kernels for Dialogue Topic Tracking
- 12:00 Contextual Domain Classification in Spoken Language Understanding Systems Using Recurrent Neural Network
- 12:20 Coping with language data sparsity: semantic head mapping of compound words
- 12:40 Reranked aligners for interactive transcript correction
IVMSP-L1: Image Quality Assessment
Room: Volta
Chair: David L Neuhoff (University of Michigan, USA)
- 11:00 Learning Sparse Models for Image Quality Assessment
- 11:20 Subjective Similarity Evaluation for Scenic Bilevel Images
- 11:40 Full-Reference and Reduced-Reference Quality Metrics based on SIFT
- 12:00 Towards a novel perceptual color difference metric using circular processing of hue components
- 12:20 GEQM: A Quality Metric for Gray-Level Edge Maps Based on Structural Matching
- 12:40 Missing Intensity Restoration via Perceptually Optimized Subspace Projection Based on Entropy Component Analysis
SLTC-P1: Deep Neural Networks in Speech Recognition I
Room: Poster Area 1
Chair: Dong Yu (Microsoft Research, USA)
- SLTC-P1.1 Mean-Normalized Stochastic Gradient For Large-Scale Deep Learning
- SLTC-P1.2 Extracting deep neural network bottleneck features using low-rank matrix factorization
- SLTC-P1.3 Combining Time- and Frequency-Domain Convolution in Convolutional Neural Network-Based Phone Recognition
- SLTC-P1.4 On Combining DNN and GMM with Unsupervised Speaker Adaptation for Robust Automatic Speech Recognition
- SLTC-P1.5 An Ideal Hidden-Activation Mask for Deep Neural Networks based Noise-Robust Speech Recognition
- SLTC-P1.6 Kernel Methods match Deep Neural Networks on TIMIT
- SLTC-P1.7 Deep Scattering Spectrum With Deep Neural Networks
- SLTC-P1.8 improving deep neural network acoustic models using generalized maxout networks
- SLTC-P1.9 Transcribing Code-switched Bilingual Lectures using Deep Neural Networks with Unit Merging in Acoustic Modeling
- SLTC-P1.10 Improving DNN speaker independence with $i$-vector inputs
- SLTC-P1.11 Context Dependent State Tying for Speech Recognition using Deep Neural Network Acoustic Models
- SLTC-P1.12 On Parallelizability of Stochastic Gradient Descent for Speech DNNs
- SLTC-P1.13 Stochastic Data Sweeping For Fast DNN Training
- SLTC-P1.14 Reshaping Deep Neural Network for Fast Decoding by Node-pruning
SLTC-P2: Stochastic Speech Synthesis
Room: Poster Area 2
Chair: Masami Akamine (Toshiba, Japan)
- SLTC-P2.1 Natural Speech Synthesis Based On Hybrid Approach with Candidate Expansion and Verification
- SLTC-P2.2 A Comparative Evaluation of Vocoding Techniques for HMM-based Laughter Synthesis
- SLTC-P2.3 Excitation Modeling for HMM-based Speech Synthesis: Breaking Down the Impact of Periodic and Aperiodic Components
- SLTC-P2.4 HMM-based singing voice synthesis and its application to Japanese and English
- SLTC-P2.5 Effectiveness of PLP-based Phonetic Segmentation for Speech Synthesis
- SLTC-P2.6 A frequency-weighted post-filtering transform for compensation of the over-smoothing effect in HMM-based speech synthesis
- SLTC-P2.7 Cluster Adaptive Training of Average Voice Models
- SLTC-P2.8 Multiple-Average-Voice-based Speech Synthesis
- SLTC-P2.9 A postfilter to modify the modulation spectrum in HMM-based speech synthesis
- SLTC-P2.10 a novel hybrid mandarin speech synthesis system using different base units for model training and concatenation
- SLTC-P2.11 Linear Dynamical Models in Speech Synthesis
SPTM-P1: Time Frequency Analysis, System Modelling and Estimation
Room: Poster Area 3
Chair: Steve McLaughlin (Heriot Watt University, United Kingdom)
- SPTM-P1.1 Extending Multifractal Analysis to Negative Regularity: p-exponents and p-Leaders
- SPTM-P1.2 Efficient Kernel-Based Formulations of Spatio-Spectral and Related Transformations on the 2-Sphere
- SPTM-P1.3 The Fourier-based Synchrosqueezing Transform
- SPTM-P1.4 A new nonparametric method for testing stationarity based on trend analysis in the time marginal distribution
- SPTM-P1.5 On selecting relevant intrinsic mode functions in empirical mode decomposition: an energy-based approach
- SPTM-P1.6 State and impulsive time-varying measurement noise density estimation in nonlinear dynamic systems using Dirichlet Process Mixtures
- SPTM-P1.7 Sparse regressions for joint segmentation and linear prediction
- SPTM-P1.8 Extending coherence time for analysis of modulated random processes
- SPTM-P1.9 Time-Frequency Signature Reconstruction from Random Observations Using Multiple Measurement Vectors
- SPTM-P1.10 Block-Recursive IAA-based Spectral Estimates with Missing Samples using data interpolation
SPTM-P2: Signal and System Modelling, and Estimation I
Room: Poster Area 4
Chair: Victor Solo (University of New South Wales, Australia)
- SPTM-P2.1 Distributions of Upper PAPR and Lower PAPR of OFDM Signals in Visible Light Communications
- SPTM-P2.2 The Farey-dictionary for sparse representation of periodic signals
- SPTM-P2.3 Sparse Linear Operator Identification without Sparse Regularization? Applications to Mixed Pixel Problem in Time-of-Flight / Range Imaging
- SPTM-P2.4 Optimization with sums of exponentials and applications
- SPTM-P2.5 Topology Identification of Dynamic Point Process Networks
- SPTM-P2.6 A unique polar representation of the hyperanalytic signal
- SPTM-P2.7 Autoconvolution and panorama: Augmenting second-order signal analysis
- SPTM-P2.8 A Multidimensional Signal Processing Approach to Wave Digital Filters with Topology-Related Delay-Free Loops
- SPTM-P2.9 Estimation of Rank Deficient Covariance Matrices with Kronecker Structure
- SPTM-P2.10 Anomaly detection for dike monitoring using system identification
- SPTM-P2.11 Noise Squared Norm in OFDM Systems Interfered by Impulse Noise
- SPTM-P2.12 Gaussian process parameter estimation using zero crossing data from wireless sensors
- SPTM-P2.13 The Cramer-Rao bound for Estimation-After-Selection
- SPTM-P2.14 Compression-based normal similarity measures for DNA sequences
SPCOM-P1: Coordinated transmission in heterogeneous networks
Room: Poster Area 5
Chair: Min Dong (University of Ontario Institute of Technology, Canada)
- SPCOM-P1.1 Order statistics based CDF scheduling methods in Multiuser Heterogeneous Systems
- SPCOM-P1.2 Robust Spectrum Management with Incomplete Information
- SPCOM-P1.3 Joint Power Allocation, Base Station Assignment and Beamformer Design for an Uplink SIMO Heterogeneous Network
- SPCOM-P1.4 A Context-Aware Matching Game for User Association in Wireless Small Cell Networks
- SPCOM-P1.5 Matching Theory for Priority-Based Cell Association in the Downlink of Wireless Small Cell Networks
- SPCOM-P1.6 Optimal Resource Allocation for Type-II HARQ based OFDMA Ad Hoc Networks under Individual Rate and Power Constraints
- SPCOM-P1.7 Globally optimal joint uplink base station association and power control for max-min fairness
- SPCOM-P1.8 Coordinated Downlink and Uplink User Association and Beamforming for Energy Minimization in Cloud Radio Access Network
- SPCOM-P1.9 Cooperative Multi-Cell MIMO Downlink Precoding for Finite-Alphabet Inputs
- SPCOM-P1.10 Decentralized Sum MSE Minimization for Coordinated Multi-Point Transmission
- SPCOM-P1.11 Power allocation for Gaussian multiple access channel with noisy cooperative links
- SPCOM-P1.12 Weighted Sum Rate Optimization for Multicell MIMO Systems with Hardware-Impaired Transceivers
- SPCOM-P1.13 Coordinated beamforming in MIMO FBMC/OQAM systems
- SPCOM-P1.14 Joint Precoding over a Master-slave Coordination Link
IVMSP-P1: Face Recognition
Room: Poster Area 6
Chair: Yu-hen Hu (University of Wisconsin-Madison, USA)
- IVMSP-P1.1 Multiple-View Constrained Clustering For Unsupervised Face Identification In TV-Broadcast
- IVMSP-P1.2 Face Recognition based on Sigma Sets of Image Features
- IVMSP-P1.3 Log-domain polynomial filters for illumination-robust face recognition
- IVMSP-P1.4 Probabilistic Linear Discriminant Analysis for intermodality face recognition
- IVMSP-P1.5 Regularized Shearlet Network For Face Recognition Using Single Sample Per Person
- IVMSP-P1.6 Histogram of Log-Gabor Magnitude Patterns for Face Recognition
- IVMSP-P1.7 Facial Image De-identification using Identity Subspace Decomposition
- IVMSP-P1.8 Polynomial based texture representation for facial expression recognition
IVMSP-P2: Stereoscopic and 3D Processing
Room: Poster Area 7
Chair: Truong Nguyen (University of California, San Diego, USA)
- IVMSP-P2.1 Analysis of the Effect of Calibration Error on Light Field Super-Resolution Rendering
- IVMSP-P2.2 Efficient intra prediction scheme for light field image compression
- IVMSP-P2.3 Adaptive Block Truncation Filter for MVC Depth Image Enhancement
- IVMSP-P2.4 Generic 2D/3D Smoothing via Regional Variation
- IVMSP-P2.5 Temporally coherent stereo matching using kinematic constraints
- IVMSP-P2.6 Performance Analysis in Lytro Camera: Empirical and Model Based Approaches to Assess Refocusing Quality
- IVMSP-P2.7 An efficient algorithm for pothole detection using stereo vision
- IVMSP-P2.8 Toward A One Shot Multi-Projector Profilometry System For Full Field Of View Object Measurement
- IVMSP-P2.9 Efficient 3-Dimensional Model Reconstruction Based on Marker Encoded Fringe Projection Profilometry
- IVMSP-P2.10 Low-saliency Prior for Disocclusion Hole Filling in DIBR-synthesized Images
- IVMSP-P2.11 Hierarchical Depth Processing with Adaptive Search Range and Fusion
- IVMSP-P2.12 Using Monocular Depth Cues for Modeling Stereoscopic 3D Saliency
- IVMSP-P2.13 An Improved Model of Binocular Energy Calculation For Full-Reference Stereoscopic Image Quality Assessment
- IVMSP-P2.14 Label Propagation Through Edge-preserving Filters
AASP-P1: Microphone Array Processing I, Music Analysis and Synthesis I
Room: Poster Area 8
Chair: Gaël Richard (Institut Mines-Télécom, Télécom ParisTech, CNRS-LTCI, France)
- AASP-P1.1 Close-talking spherical microphone array using sound pressure interpolation based on spherical harmonic expansion
- AASP-P1.2 Time-Delay Estimation for TOA-Based Localization of Multiple Sensors
- AASP-P1.3 Multi-Speaker Tracking using Multiple Distributed Microphone Arrays
- AASP-P1.4 Sound-Model-Based Acoustic Source Localization using Distributed Microphone Arrays
- AASP-P1.5 Cultivating Vocal Activity Detection for Music Audio Signals in a Circulation-type Crowdsourcing Ecosystem
- AASP-P1.6 A Pairwise Approach to Simultaneous Onset/Offset Detection for Singing Voice using Correntropy
- AASP-P1.7 Parametric model of spectral envelope to synthesize realistic intensity variations in singing voice
- AASP-P1.8 Exploiting global features for tempo octave correction
- AASP-P1.9 An Audio Fingerprinting System for Live Version Identification using Image Processing Techniques
- AASP-P1.10 Accounting for Phase Cancellations in Non-Negative Matrix Factorization Using Weighted Distances
- AASP-P1.11 Estimating Timing and Channel Distortion Across Related Signals
- AASP-P1.12 PYIN: a Fundamental Frequency Estimator Using Probabilistic Threshold Distributions
- AASP-P1.13 Music Segment Similarity Using 2D-Fourier Magnitude Coefficients
MMSP-P1: Multimedia Communication and Interaction
Room: Poster Area 9
Chairs: Homer Chen (National Taiwan University & National Taiwan University, Taiwan), Frederic Dufaux (Telecom Paristech & CNRS, France)
- MMSP-P1.1 Attention-Weighted Rate Allocation in Free-Viewpoint Television
- MMSP-P1.2 Stereoscopic image retargeting based on 3D saliency detection
- MMSP-P1.3 Prediction-based Load Control and Balancing for Feature Extraction in Visual Sensor Networks
- MMSP-P1.4 MangaWall: Generating Manga Pages for Real-Time Applications
- MMSP-P1.5 Towards Optimal Resource Allocation for Differentiated Multimedia Services in Cloud Computing Environment
- MMSP-P1.6 Source Localization on Solids Utilizing Time-frequency Analysis of Parameterized Warped Signals
- MMSP-P1.7 Analysis and Modeling of Next Speaking Start Timing based on Gaze Behavior in Multi-party Meetings
- MMSP-P1.8 Analysis of Interaction Attitudes Using Data-driven Hand Gesture Phrases
- MMSP-P1.9 Bandit Framework for Systematic Learning in Wireless Video-based Face Recognition
- MMSP-P1.10 Optimal Foresighted Packet Scheduling and Resource Allocation for Multi-user Video Transmission in 4G Cellular Networks
- MMSP-P1.11 Quality-fair HTTP Adaptive Streaming over LTE Network
- MMSP-P1.12 Automatic Inference of Mental States from Spontaneous Facial Expressions
- MMSP-P1.13 Segmentation of music video streams in music pieces through audio-visual analysis
1:00 PM - 2:45 PM
Lunch Time
2:45 PM - 3:45 PM
PT1: Plenary Talk: Signal Processing in Computational Art History (Room Cavaniglia)
Keynote speaker: C. Richard Johnson, Jr.
3:45 PM - 4:15 PM
Coffee break
4:15 PM - 6:15 PM
SLTC-L3: Speaker recognition I
Room: Cavaniglia
Chairs: Anthony Larcher (Institute for Infocomm Research & A*STAR, Singapore), Pedro Torres-Carrasquillo (MIT Lincoln Laboratory, USA)
- 4:15 Text-dependent GMM-JFA system for password based speaker verification
- 4:35 Modelling the Alternative Hypothesis for Text-Dependent Speaker Verification
- 4:55 Imposture classification for Text-Dependent Speaker Verification
- 5:15 Unsupervised Adaptation of PLDA by Using Variational Bayes Methods
- 5:35 Evasion and obfuscation in automatic speaker verification
- 5:55 A Wrapped Kalman Filter for Azimuthal Speaker Tracking
SPTM-L2: Signal and System Modelling, and Estimation II
Room: Basilica
Chairs: Yonina C. Eldar (Technion-Israel Institute of Technology, Israel), Antonio Napolitano (Universita di Napoli Parthenope, Italy)
- 4:15 An Algorithm for Exact Super-resolution and Phase Retrieval
- 4:35 Estimation of phase synchrony using the synchrosqueezing transform
- 4:55 Wide-Band Moving Source Passive Localization in Highly Corruptive Environments
- 5:15 Compressive Nonparametric Graphical Model Selection for Time Series
- 5:35 3D Rotation Estimation Using Discrete Spherical Harmonic Oscillator Transforms
- 5:55 Smooth Time-Frequency Estimation using Covariance Fitting
SS2: Enhanced Radar Sensing in Harsh Environments Phenomenology
Room: Polveriera
Chair: Yuriy V. Shkvarko (Cinvestav Jalisco, Mexico)
- 4:15 Multilevel descriptive experiment design regularization framework for sparsity preserving enhancement of radar imagery in harsh sensing environments
- 4:35 Multi-Band Radio-Frequency Integrated Circuits for Multiband and Multimode Wireless Communication, Radar and Sensing Systems in Harsh Environments
- 4:55 Detection, Parametric Imaging and Classification of Very Small Marine Targets Emerged in Heavy Sea Clutter Utilizing GPS-Based Forward Scattering Radar
- 5:15 Radar tomography using noise waveform, antenna with beam synthesis and MIMO principle
- 5:35 Over-the-Horizon Radar Potential Signal Parameter Estimation Accuracy in Harsh Sensing Environments
- 5:55 Polarimetric MIMO Radar Target Detection Based on Glowworm Swarm Optimization Algorithm
AASP-L1: Microphone-Array Beamforming
Room: Scherma
Chairs: Jingdong Chen (Northwestern Polytechnical University, USA), Nobutaka Ono (National Institute of Informatics, Japan)
- 4:15 Diffusion-Based Distributed MVDR Beamformer
- 4:35 On the Noise Reduction Performance of the MVDR Beamformer in Noisy and Reverberant Environments
- 4:55 A New Generalized Sidelobe Canceller with a Compact Array of Microphones Suitable for Mobile Terminals
- 5:15 Multichannel Wiener Filter Performance Analysis in Presence of Mismodeling
- 5:35 Automatic spatial gain control for an informed spatial filter
- 5:55 An Analysis of Binaural Spectro-temporal Masking as Nonlinear Beamforming
SPCOM-L1: Resource allocation
Room: Teatrino
Chairs: Timothy N. Davidson (McMaster University, Canada), Gesualdo Scutari (State University of New York at Buffalo, USA)
- 4:15 Parallel and Distributed Methods for Nonconvex Optimization
- 4:35 Max-Min Network Flow and Resource Allocation for Backhaul Constrained Heterogeneous Wireless Networks
- 4:55 Joint cell selection and radio resource allocation in MIMO small cell networks via successive convex approximation
- 5:15 Near-Optimal Spectrum Allocation in Multi-tier Cellular Networks with Random Inelastic Traffic
- 5:35 Queue Aware Precoder Design for Space Frequency Resource Allocation
- 5:55 Effectiveness of successive interference cancellation and association policies for heterogeneous wireless networks
IVMSP-L2: Stereoscopic and 3D coding
Room: Volta
Chair: Gene Cheung (National Institute of Informatics, Japan)
- 4:15 Quad-tree partitioned compressed sensing for depth map coding
- 4:35 Flexible depth map spatial resolution in depth-enhanced multiview video coding
- 4:55 Asymmetric Coding using Binocular Just Noticeable Difference and Depth Information for Stereoscopic 3D
- 5:15 A Graph-based Joint Bilateral Approach for Depth Enhancement
- 5:35 Synthesis Error Compensated Multiview Video Plus Depth For Representation of Multiview Video
- 5:55 A Low Complexity Mode Decision Approach for HEVC-based 3D Video Coding Using a Bayesian Method
SLTC-P3: Speech Production and Perception
Room: Poster Area 1
Chair: Douglas O'Shaughnessy (INRS-Énergie-Matériaux-Télécommunications, Canada)
- SLTC-P3.1 Robust and efficient environment detection for adaptive speech enhancement in cochlear implants
- SLTC-P3.2 Improving Channel Selection of Sound Coding Algorithms in Cochlear Implants
- SLTC-P3.3 Speech Reinforcement in Noisy Reverberant Environments Using a Perceptual Distortion Measure
- SLTC-P3.4 Modeling pathological speech perception from data with similarity labels
- SLTC-P3.5 Closed Phase Estimation for Inverse Filtering the Oral Airflow Waveform
- SLTC-P3.6 Perceived quality of resonance based decomposed speech components under diotic and dichotic listening
- SLTC-P3.7 Signal Processing Methods for Removing the Effects of Whole-Body Vibration Upon Speech
- SLTC-P3.8 Vowel-reduction feedback system for non-native learners of English
- SLTC-P3.9 Maximum a-posteriori estimation of missing samples with continuity constraint in electromagnetic articulography data
- SLTC-P3.10 Subband Analysis of Linear Prediction Residual for the Estimation of Glottal Closure Instants
SLTC-P4: Processing of Abnormal Speech
Room: Poster Area 2
Chair: Thomas Quatieri (MIT, USA)
- SLTC-P4.1 On Automatic Voice Casting for Expressive Speech: Speaker Recognition vs. Speech Classification
- SLTC-P4.2 Fusion of Acoustic, Linguistic and Psycholinguistic Features for Speaker Personality Traits Recognition
- SLTC-P4.3 COVAREP - A collaborative voice analysis repository for speech technologies
- SLTC-P4.4 Automatic Measurement Of Affective Valence And Arousal In Speech
- SLTC-P4.5 Variability Compensation in Small Data: Oversampled Extraction of i-vectors for the Classification of Depressed Speech
- SLTC-P4.6 Analysis of Laughter and Speech-Laugh Signals using Excitation Source Information
- SLTC-P4.7 Multi-scale modulation filtering in automatic detection of emotions in telephone speech
- SLTC-P4.8 Bivariate Analysis of Disordered Connected Speech Using Temporal and Spectral Acoustic Cues
- SLTC-P4.9 Modeling Gender Information for Emotion Recognition Using Denoising Autoencoders
- SLTC-P4.10 Are Men more Sleepy than Women or does it only Look like - Automatic Analysis of Sleepy Speech
SPTM-P3: Compressed Sensing I
Room: Poster Area 3
Chair: Moeness G. Amin (Villanova University, USA)
- SPTM-P3.1 Monte Carlo Methods for Compressed Sensing
- SPTM-P3.2 Exact Performance Analysis of the Oracle Receiver for Compressed Sensing Reconstruction
- SPTM-P3.3 Off-The-Grid Spectral Compressed Sensing With Prior Information
- SPTM-P3.4 Compressive Signal Processing with Circulant Sensing Matrices
- SPTM-P3.5 Adaptive Compressed Classification For Hyperspectral Imagery
- SPTM-P3.6 Shrinkage mappings and their induced penalty functions
- SPTM-P3.7 Block-Sparse Signal Recovery with Synthesized Multitask Compressive Sensing
- SPTM-P3.8 Joint Sparsity and Frequency Estimation for Spectral Compressive Sensing
- SPTM-P3.9 Compressed sensing with unknown sensor permutation
- SPTM-P3.10 Spectral Compressive Sensing with Model Selection
- SPTM-P3.11 Robust Sparse Signal Recovery Based on Weighted Median Operator
- SPTM-P3.12 Compressed matched filter for non-Gaussian noise
- SPTM-P3.13 Power Spectrum Blind Sampling using Optimal Multicoset Sampling Patterns in the MSE sense
- SPTM-P3.14 Specular Multipath Exploitation for Improved Velocity Estimation in Through-the-Wall Radar Imaging
SPTM-P4: Signal Processing over Graphs I
Room: Poster Area 4
Chair: Jose Moura (Carnegie Mellon University, USA)
- SPTM-P4.1 Nonnegative matrix factorization to find features in temporal networks
- SPTM-P4.2 Coarsening Graph Signal with Spectral Invariance
- SPTM-P4.3 All For One, One For All: Consensus Community Detection in Networks
- SPTM-P4.4 Finite-Time Distributed Consensus Through Graph Filters
- SPTM-P4.5 Spectral Anomaly Detection using Graph-based Filtering for Wireless Sensor Networks
- SPTM-P4.6 Churn Detection in Large User Networks
- SPTM-P4.7 Modeling Information Diffusion Dynamics over Social Networks
- SPTM-P4.8 Distributed demand side management of heterogeneous rational consumers in smart grids with renewable sources
- SPTM-P4.9 A Distributed Consensus Plus Innovation Particle Filter for Networks with Communication Constraints
- SPTM-P4.10 Distributed On-line Multidimensional Scaling for self-Localization in Wireless Sensor Networks
- SPTM-P4.11 Dynamic Diffusion Estimation in Exponential Family Models
- SPTM-P4.12 Semi-Supervised Learning for Graph to Signal Mapping: a Graph Signal Wiener Filter Interpretation
- SPTM-P4.13 Local Fiedler Vector Centrality for Detection of Deep and Overlapping Communities in Networks
- SPTM-P4.14 Subgraph Density and Epidemics over Networks
SPCOM-P2: Interference alignment
Room: Poster Area 5
Chair: Dimitris A. Pados (The State University of New York at Buffalo, USA)
- SPCOM-P2.1 Achieving the Degrees of Freedom of $2\times 2\times 2$ Interference Network with arbitrary antenna configurations
- SPCOM-P2.2 Location Aided Semi-Blind Interference Alignment for Clustered Small Cell Networks
- SPCOM-P2.3 Improper Gaussian signaling for the Z-interference channel
- SPCOM-P2.4 On the Degrees of Freedom of Partially-Connected Symmetrically-Configured MIMO Interference Broadcast Channels
- SPCOM-P2.5 Precoding for Systems with Soft Combining to Counteract Instationary Intercell Interference
- SPCOM-P2.6 On the Degrees of freedom of the K-user MISO Interference Channel with imperfect delayed CSIT
- SPCOM-P2.7 New Feedback Topology Designs with Reduced CSI Overhead for MIMO Interference Alignment
- SPCOM-P2.8 Ergodic Interference Alignment With Delayed Feedback
- SPCOM-P2.9 Opportunistic Scheduling With BIA Under Block Fading Broadcast Channels
- SPCOM-P2.10 Receiver-Coordinated Distributed Transmit Nullforming with Local and Unified Tracking
IVMSP-P3: Image Restoration and Enhancement
Room: Poster Area 6
Chair: William Karl (Boston University, USA)
- IVMSP-P3.1 A Low-Complexity 3D Spatio-Temporal FIR Filter for Enhancing Linear Trajectory Signals
- IVMSP-P3.2 Metal Artifact Reduction for CT-Based Luggage Screening
- IVMSP-P3.3 Structure-preserving dual-energy CT for luggage screening
- IVMSP-P3.4 Adaptive 2D-AR framework for texture completion
- IVMSP-P3.5 Flash/No-flash Image Integration Using Convex Optimization
- IVMSP-P3.6 A Novel Retinex Based Approach for Image Enhancement with Illumination Adjustment
- IVMSP-P3.7 Fusion of Tone-Mapped High Dynamic Range Images Based on Objective Range-Independent Quality Maps
- IVMSP-P3.8 Adaptive Windowing for Optimal Visualization of Medical Images Based on Normalized Information Distance
- IVMSP-P3.9 Power-Constrained RGB-to-RGBW Conversion for Emissive Displays
- IVMSP-P3.10 Color transform between image pair using covariance correspondences of local color distributions
- IVMSP-P3.11 Image Colorization Algorithm Using Series Approximated Sparse Function
- IVMSP-P3.12 SSIM Performance Limitation of Linear Equalizers
- IVMSP-P3.13 Poisson denoising with multiple Directional LOTs
- IVMSP-P3.14 Unbiased noise estimation and denoising in Parallel Magnetic Resonance Imaging
IVMSP-P4: Video Analysis
Room: Poster Area 7
Chair: Carlo S Regazzoni (University Of Genova, Italy)
- IVMSP-P4.1 Learning Directional Co-occurrence for Human Action Classification
- IVMSP-P4.2 Spontaneous Versus Posed Smile Recognition Using Discriminative Local Spatial-temporal Descriptors
- IVMSP-P4.3 Text Detection and Recognition in Natural Scenes and Consumer Videos
- IVMSP-P4.4 Exploiting Transfer Learning For Personalized View Invariant Gesture Recognition
- IVMSP-P4.5 Alignment of Nearly-repetitive Contents in a Video Stream with Manifold Embedding
- IVMSP-P4.6 Low Complexity On-line Video Summarization with Gaussian Mixture Model Based Clustering
- IVMSP-P4.7 Tensor-variate Gaussian Processes Regression and Its Application to Video Surveillance
- IVMSP-P4.8 Spatio-Temporal Pyramidal Accordion Representation for Human Action Recognition
- IVMSP-P4.9 Gesture recognition using a NMF-based representation of motion-traces extracted from depth silhouettes
- IVMSP-P4.10 Visual odometry for RGB-D cameras for dynamic scenes
- IVMSP-P4.11 Low Rank Sparsity Prior for Robust Video Anomaly Detection
- IVMSP-P4.12 Detection of sign-language content in video through polar motion profiles
- IVMSP-P4.13 An Advanced Codebook Background Model Using Confidence and Membership Function
AASP-P2: Echo Control I, Quality Measure
Room: Poster Area 8
Chair: Israel Cohen (Technion, Israel)
- AASP-P2.1 State-Space Architecture of the Partitioned-Block-Based Acoustic Echo Controller
- AASP-P2.2 Robust acoustic echo cancellation in the short-time Fourier transform domain using adaptive crossband filters
- AASP-P2.3 Accurate adaptive filtering in square-root Hann windowed short-time Fourier transform domain
- AASP-P2.4 Avoiding Local Trap in Nonlinear Acoustic Echo Cancellation with Clipping Compensation
- AASP-P2.5 The elitist particle filter based on evolutionary strategies as novel approach for nonlinear acoustic echo cancellation
- AASP-P2.6 Non-Linear Acoustic Echo Cancellation Using Cascaded Kalman Filtering
- AASP-P2.7 Speech and audio loudness depending on telephone audio bandwidth and codec - A subjective testing approach
- AASP-P2.8 Objective Evaluation of the Audibility of Transient Errors in an Adaptive A/D Conversion Channel
- AASP-P2.9 Signal Quality Classification of Mobile Phone-Recorded Phonocardiogram Signals
- AASP-P2.10 Quality assessment of multi-channel audio processing schemes based on a binaural auditory model
- AASP-P2.11 Crossband Filtering for Stereophonic Acoustic Echo Suppression
MMSP-P2: Multimedia Systems, Databases, and Quality Assessment
Room: Poster Area 9
Chair: Homer Chen (National Taiwan University & National Taiwan University, Taiwan)
- MMSP-P2.1 Improving Time-Scale Modification of Music Signals Using Harmonic-Percussive Separation
- MMSP-P2.2 Deep learning vector quantization for acoustic information retrieval
- MMSP-P2.3 Simultaneous Acquisition of Multiple Images with Higher Dynamic Range
- MMSP-P2.4 Exploring audio semantic concept for event-based video retrieval
- MMSP-P2.5 Improved Score-Performance Alignment Algorithms On Polyphonic Music
- MMSP-P2.6 Softening Quantization in Bag-of-Audio-Words
- MMSP-P2.7 semi-automatic audio semantic concept discovery for multimedia retrieval
- MMSP-P2.8 Chinese image text recognition on grayscale pixels
- MMSP-P2.9 Quality assessment of online videos using metadata
- MMSP-P2.10 Auditory Attention Based Mobile Audio Quality Assessment
- MMSP-P2.11 A Power Mask based Audio Fingerprint
- MMSP-P2.12 A Monolithic Programmable Ultra-HD Video Codec Engine
SAM-P1: Localization and Tracking
Room: Poster Area 10
Chair: Mounir Ghogho (University of Leeds & International University of Rabat, United Kingdom)
- SAM-P1.1 Matched field processing localization with random sensor topologies
- SAM-P1.2 Weighted Stansfield Algorithm in Three Dimensions
- SAM-P1.3 Novel Closed-form Auxiliary Variables Based Algorithms for Sensor Node Localization Using AOA
- SAM-P1.4 Reaching Asymptotic Efficient Performance for Squared Processing of Range and Range Difference Localizations in the Presence of Sensor Position Errors
- SAM-P1.5 A Binaural Sound Source Localization Model Based on Time-Delay Compensation and Interaural Coherence
- SAM-P1.6 Source Localization and Tracking in Non-Convex Rooms
- SAM-P1.7 Single-Channel Indoor Microphone Localization
- SAM-P1.8 Model-based Sparse Component Analysis for Reverberant Speech Localization
- SAM-P1.9 Multiple Concurrent Speaker Short-Term Tracking Using A Kalman Filter Bank
- SAM-P1.10 Adaptive Waveform Scheduling for Target Tracking in Clutter by Multistatic Radar System
- SAM-P1.11 Motion Parameter Estimation of Multiple Targets in Multistatic Passive Radar Through Sparse Signal Recovery
- SAM-P1.12 Environmentally Sensitive Particle Filter Tracking in Multistatic AUV Networks with Port-Starboard Ambiguity
- SAM-P1.13 Joint Emitter Detection and Tracking using Distributed Random Exchange Diffusion Particle Filtering
Wednesday, May 7
8:30 AM - 10:30 AM
SLTC-L4: Fundamental Frequency Estimation
Room: Cavaniglia
Chairs: Malcolm Slaney (Microsoft Research & Stanford University, USA), DeLiang Wang (Ohio State University, USA)
- 8:30 Robust F0 Estimation in Noisy Speech Signals Using Shift Autocorrelation
- 8:50 Multi-pitch tracking using Gaussian mixture model with time varying parameters and Grating Compression Transform
- 9:10 A Computationally Efficient Refinement of the Fundamental Frequency Estimate for the Adaptive Harmonic Model
- 9:30 A Robust Pitch Detector Based on Time Envelope and Individual Harmonic Information using Phase Locked Loops and Consensual Decisions
- 9:50 Neural Networks For Supervised Pitch Tracking in Noise
- 10:10 Epoch Extraction from Allpass Residual of Speech Signals
SS3: Optimization algorithms for high dimensional signal processing
Room: Basilica
Chairs: Volkan Cevher (Ecole Polytechnique Federale de Lausanne, Switzerland), Mário A. T. Figueiredo (Instituto Superior Técnico & Instituto de Telecomunicações, Portugal)
- 8:30 A preconditioned forward-backward approach with application to large-scale nonconvex spectral unmixing problems
- 8:50 Iteration-Complexity of a Generalized Forward Backward Splitting Algorithm
- 9:10 Barrier smoothing for nonsmooth convex minimization
- 9:30 Distributed Nesterov Gradient Methods for Random Networks: Convergence in Probability and Convergence Rates
- 9:50 Teaching a new trick to an old dog: revisiting the quadratic programming formulation of sparse recovery using ADMM
- 10:10 Active set strategy for high-dimensional non-convex sparse optimization problems
MMSP-L1: Multimedia and Multimodal Signal Processing I
Room: Polveriera
Chairs: Peter Schelkens (Vrije Universiteit Brussel, Belgium), Vanessa Testoni (Samsung Research, Brazil)
- 8:30 Robust Canonical Correlation Analysis: Audio-visual Fusion for Learning Continuous Interest
- 8:50 A new EM estimation of dynamic stream weights for coupled-HMM-based audio-visual ASR
- 9:10 Look Who's Talking: Detecting the Dominant Speaker in a Cluttered Scenario
- 9:30 Motion history images for online speaker/signer diarization
- 9:50 Multimodal Voice Conversion using Non-Negative Matrix Factorization in Noisy Environments
- 10:10 Bag of sub-graphs for video event recognition
AASP-L2: Speech and Audio Enhancement
Room: Scherma
Chairs: Shoji Makino (University of Tsukuba, Japan), Jonathan Le Roux (Mitsubishi Electric Research Laboratories, USA)
- 8:30 Examples of Optimal Noise Reduction Filters Derived from the Squared Pearson Correlation Coefficient
- 8:50 Fast segment search for corpus-based speech enhancement based on speech recognition technology
- 9:10 Deep Learning for Monaural Speech Separation
- 9:30 An interactive audio source separation framework based on non-negative matrix factorization
- 9:50 Towards complex matrix decomposition of spectrograms based on the relative phase offsets of harmonic sounds
- 10:10 Audio Declipping with Social Sparsity
SS4: Signal Processing for Cyber-Security and Privacy
Room: Teatrino
Chairs: Holger Boche (Technical University Munich, Germany), Rafael F. Schaefer (Princeton University, USA)
- 8:30 On the Use of Secret Keys in Broadcast Channels with Receiver Side Information
- 8:50 Mobi-Cliques for Improving Ergodic Secrecy in Fading Wiretap Channels under Power Constraints
- 9:10 Precoding for Secret Key Generation in Multiple Antenna Channels with Statistical Channel State Information
- 9:30 Robust Artificial Noise-aided Transmit Optimization for Achieving Secrecy and Energy Harvesting
- 9:50 Privacy-leakage codes for biometric authentication systems
- 10:10 Device-to-Device Communications:The Physical Layer Security Advantage
BISP-L1: Biomedical Informatics and Image Analysis I
Room: Volta
Chairs: Scott Acton (University of Virginia, USA), William Karl (Boston University, USA)
- 8:30 A Non-Homogeneous Poisson Process Model of Skin Conductance Responses Integrated with Observed Regulatory Behaviors for Autism Intervention
- 8:50 Joint Clustering of Protein Interaction Networks by Block Modeling
- 9:10 Using Density Invariant Graph Laplacian to Resolve Unobservable Parameters for Three-Dimensional Optical Bio-imaging
- 9:30 Deep Learning of Feature Representation with Multiple Instance Learning for Medical Image Analysis
- 9:50 Exponential Hermite Splines for the Analysis of Biomedical Images
- 10:10 An Adaptive Distributed Resampling Algorithm with Non-Proportional Allocation
SLTC-P5: Speaker recognition II
Room: Poster Area 1
Chair: Nicholas Evans (EURECOM, France)
- SLTC-P5.1 An Investigation of Summed-channel Speaker Recognition with Multi-session Enrollment
- SLTC-P5.2 Training pairwise Support Vector Machines with large scale datasets
- SLTC-P5.3 Large-scale speaker identification
- SLTC-P5.4 Spear: An Open Source Toolbox for Speaker Recognition Based on Bob
- SLTC-P5.5 Speaker Verification Using Kernel-Based Binary Classifiers with Binary Operation Derived Features
- SLTC-P5.6 Improving PLDA speaker verification with limited development data
- SLTC-P5.7 Constrained discriminative PLDA training for speaker verification
- SLTC-P5.8 Unsupervised Idiolect Discovery for Speaker Recognition
- SLTC-P5.9 Generative Modelling for Unsupervised Score Calibration
- SLTC-P5.10 Bayesian vocal tract model estimates of nasal stops for speaker verification
- SLTC-P5.11 Physiologically-motivated Feature Extraction for Speaker Identification
- SLTC-P5.12 A novel scheme for speaker recognition using a phonetically-aware deep neural network
- SLTC-P5.13 Deep Belief Networks for i-vector Based Speaker Recognition
- SLTC-P5.14 JFA-Based Front Ends for Speaker Recognition
SLTC-P6: Robust Speech Recognition I
Room: Poster Area 2
Chair: Jinyu Li (Microsoft Corporation, USA)
- SLTC-P6.1 Feature Enhancement using Sparse Reference and Estimated Soft-Mask Exemplar-Pairs for Noisy Speech Recognition
- SLTC-P6.2 Non-Linear Dimension Reduction of Gabor Features for Noise-Robust ASR
- SLTC-P6.3 Feature compensation using linear combination of speaker and environment dependent correction vectors
- SLTC-P6.4 Subspace Gaussian Mixture Model with State-dependent Subspace Dimensions
- SLTC-P6.5 Generalization of Temporal Filter and Linear Transformation for Robust Speech Recognition
- SLTC-P6.6 Mean normalization of power function based cepstral coefficients for robust speech recognition in noisy environments
- SLTC-P6.7 Reverberation and Noise Robust Feature Enhancement Using Multiple Inputs
- SLTC-P6.8 Semi-supervised noise dictionary adaptation for exemplar-based noise robust speech recognition
- SLTC-P6.9 Medium-duration modulation cepstral feature for robust speech recognition
- SLTC-P6.10 Exploiting a `gaze-Lombard effect' to improve ASR performance in acoustically noisy settings
- SLTC-P6.11 Speech Feature Denoising and Dereverberation via Deep Autoencoders for Noisy Reverberant speech recognition
- SLTC-P6.12 Synthesized Stereo Mapping via Deep Neural Networks for Noisy Speech Recognition
- SLTC-P6.13 Second Order Vector Taylor Series based Robust Speech Recognition
- SLTC-P6.14 Speaker verification based processing for robust ASR in co-channel speech scenarios
SPTM-P5: Sampling Theory and Methods I
Room: Poster Area 3
Chair: Josef A. Nossek (TU Munich, Germany)
- SPTM-P5.1 Quantization Noise Shaping for Information Maximizing ADCs
- SPTM-P5.2 Clock Jitter in Sampling and Reconstruction
- SPTM-P5.3 A Low-complexity Sub-Nyquist Sampling System for Wideband Radar ESM Receivers
- SPTM-P5.4 Cramér-Rao Bound for Sampling & Reconstruction of FRI Signals
- SPTM-P5.5 Jittered Random Sampling with a Successive Approximation ADC
- SPTM-P5.6 Universal Sampling of Signals with Finite Rate of Innovation
- SPTM-P5.7 Finite dimensional FRI
- SPTM-P5.8 Stable Recovery from the Magnitude of Symmetrized Fourier Measurements
- SPTM-P5.9 Sampling 2-D Signals on a Union of Lattices that Intersect on a Lattice
- SPTM-P5.10 A Model-Based Framework for Fast Dynamic Image Sampling
- SPTM-P5.11 Optimum Analog Receive Filters for Detection and Inference under a Sampling Rate Constraint
- SPTM-P5.12 Jitter Requirements for Bandpass Sampling Receivers utilizing Sample-and-Hold Circuits
- SPTM-P5.13 On the role of the Hilbert transform in boosting the performance of the annihilating filter
- SPTM-P5.14 On Conditions for Uniqueness in Sparse Phase Retrieval
SPTM-P6: Bayesian Techniques
Room: Poster Area 4
Chair: Monica F. Bugallo (Stony Brook University, USA)
- SPTM-P6.1 Bayesian Quickest Detection with Stochastic Energy Constraint
- SPTM-P6.2 Parameter Identifiability in Sparse Bayesian Learning
- SPTM-P6.3 Analysis Of The Cross-Target Measurement Fusion Likelihood For RSSI-Based Sensors
- SPTM-P6.4 Distributed data fusion using iterative covariance intersection
- SPTM-P6.5 Robust asynchronous indoor localization using LED lighting
- SPTM-P6.6 Exploiting an Event Based State Estimator in presence of sparse measurements in video analytics
- SPTM-P6.7 Optimal Information Ordering in Sequential Detection Problems with Cognitive Biases
- SPTM-P6.8 Fast Approximate L0-norm Deconvolution Using Structured Wavelet Domain Priors
- SPTM-P6.9 Non-parametric Bayesian framework for detection of object configurations with large intensity dynamics in highly noisy hyperspectral data
- SPTM-P6.10 Model Selection and Comparison for Independents Sinusoids
- SPTM-P6.11 Pattern-Coupled Sparse Bayesian Learning for Recovery of Block-Sparse Signals
- SPTM-P6.12 A hierarchical sparsity-smoothness Bayesian model for l0 + l1 + l2 regularization
SPCOM-P3: Detection and decoding
Room: Poster Area 5
Chair: Gerald Matz (Vienna University of Technology, Austria)
- SPCOM-P3.1 Joint Detection and Decoding of LDPC Coded Distributed Space-Time Signaling in Wireless Relay Networks via Linear Programming
- SPCOM-P3.2 Low complexity decoding of variable length source-channel codes
- SPCOM-P3.3 MIMO detection based on averaging Gaussian projections
- SPCOM-P3.4 Reliable packet type estimation via joint protocol-channel decoding
- SPCOM-P3.5 Reduced Complexity Sphere Decoding Using A Geometrical Approach
- SPCOM-P3.6 FER prediction with variable codeword length
- SPCOM-P3.7 Flexible Non-Binary LDPC Decoding on FPGAs
- SPCOM-P3.8 Expectation Propagation Approach to Joint Channel Estimation and Decoding for OFDM Systems
- SPCOM-P3.9 Turbo-Equalization of the Remaining Interference in a Pre-Distorted Non-Linear Satellite Channel
- SPCOM-P3.10 Partial CRC-assisted error correction of AIS signals received by satellite
- SPCOM-P3.11 LLR Optimization for Iterative MIMO BICM Receivers
- SPCOM-P3.12 An Adaptive MMSE-SIC Soft Detector with Error Regularization for Iterative MIMO Receivers
- SPCOM-P3.13 Complexity Outage Probability of MIMO Detection in Multiple-User Scenario
- SPCOM-P3.14 Channel Estimation in UWB channels using Compressed Sensing
IVMSP-P5: Image Coding and Communication
Room: Poster Area 6
Chair: Andre Kaup (University of Erlangen-Nuremberg, Germany)
- IVMSP-P5.1 Extreme Unequal Error Protection and Perfectly Reliable Encoding
- IVMSP-P5.2 Frequency Selective Extrapolation with Residual Filtering for Image Error Concealment
- IVMSP-P5.3 An Efficient Method For No-Reference H.264/SVC Bitstream Extraction
- IVMSP-P5.4 Transparent Encryption for HEVC Using Bit-Stream-Based Selective Coefficient Sign Encryption
- IVMSP-P5.5 Entropy based merging of context models for efficient arithmetic coding
- IVMSP-P5.6 Blocky Artifact Removal with Low-Rank Matrix Recovery
- IVMSP-P5.7 Running Gaussian Reference-based Reconstruction for Video Compressed Sensing
- IVMSP-P5.8 An Adaptive Lighting Correction Method for Matched-Texture Coding
- IVMSP-P5.9 Lossless/Near-Lossless Color Image Coding by Inverse Demosaicing
- IVMSP-P5.10 No-Reference Quality Assessment of HEVC Videos in Loss-Prone Networks
- IVMSP-P5.11 Accurate rate-distortion approximation for sparse Bernoulli-Generalized Gaussian models
- IVMSP-P5.12 Image Compression Via Sparse Reconstruction
- IVMSP-P5.13 A Memory-Assisted Lossless Compression Algorithm for Medical Images
- IVMSP-P5.14 A Two-Part Predictive Coder for Multitask Signal Compression
BISP-P1: EEG and fMRI data processing
Room: Poster Area 7
Chair: Fabrizio Argenti (University of Florence, Italy)
- BISP-P1.1 Robust Common Spatial Patterns by Minimum Divergence Covariance Estimator
- BISP-P1.2 Simple and Efficient Methods for Steady State Visual Evoked Potential Detection in BCI Embedded System
- BISP-P1.3 Optimizing spatial filter pairs for EEG classification based on phase synchronization
- BISP-P1.4 Automatic Removal of EEG Artifacts Using Electrode-Scalp Impedance
- BISP-P1.5 Performance estimation of a cooperative brain-computer interface based on the detection of steady-state visual evoked potentials
- BISP-P1.6 Connectivity based Feature-Level Filtering for Single-Trial EEG BCIs
- BISP-P1.7 Fingertip Force Estimation From Forearm Muscle Electrical Activity
- BISP-P1.8 Sparse Estimation of the Hemodynamic Response Function in Functional Near Infrared Spectroscopy
- BISP-P1.9 Hemodynamically Informed Parcellation of Cerebral FMRI data
- BISP-P1.10 A novel approach for assessing reliability of ICA for fMRI analysis
- BISP-P1.11 Time varying brain connectivity modeling using fMRI signals
- BISP-P1.12 Compensation of Recording Position Shifts for a Myoelectric Silent Speech Recognizer
- BISP-P1.13 Identification of Dynamic functional brain network states Through Tensor Decomposition
AASP-P3: Audio Source Separation I, Music Information Retrieval I
Room: Poster Area 8
Chair: Laurent Daudet (Université Paris Diderot, France)
- AASP-P3.1 An Alternating Least-squares Algorithm for Approximate Joint Diagonalization and Its Application to Blind Source Separation
- AASP-P3.2 Sparse Target Cancellation Filters with Application to Semi-Blind Noise Extraction
- AASP-P3.3 On the use of contextual time-frequency information for full-band clustering-based convolutive blind source separation
- AASP-P3.4 Automatic Carrier Pitch Estimation for Coherent Demodulation
- AASP-P3.5 Custom Sized Non-negative Matrix Factor Deconvolution for Sound Source Separation
- AASP-P3.6 Ultrasound-Coupled Semi-Supervised Nonnegative Matrix Factorisation for Speech Enhancement
- AASP-P3.7 Speech/music discrimination in a large database of radio broadcasts from the wild
- AASP-P3.8 Improving Music Auto-tagging by Intra-song Instance Bagging
- AASP-P3.9 Intra-note Segmentation via Sticky HMM with DP Emission
- AASP-P3.10 Linear regression-based adaptation of music emotion recognition models for personalization
- AASP-P3.11 Better beat tracking through robust onset aggregation
- AASP-P3.12 A Study of Instrument-wise Onset Detection in Beijing Opera Percussion Ensembles
- AASP-P3.13 Multi-resolution Linear Prediction Based Features for Audio Onset Detection with Bidirectional LSTM Neural Networks
IDSP-P1: Emerging Industrial Signal Processing Applications and Education
Room: Poster Area 9
Chair: Amir Said (LG Electronics Mobile Research, USA)
- IDSP-P1.1 Orbit Refinement for Software Defined Radio For Space Applications
- IDSP-P1.2 Information maximizing DAC noise shaping
- IDSP-P1.3 Face Recognition using Distributed, Mobile Computing
- IDSP-P1.4 Forecasting in wind energy applications with site-adaptive Weibull estimation
- IDSP-P1.5 Estimating an Optimal Setpoint to Lessen Errors in Filling Weighing System Based on Kalman Filtering
- IDSP-P1.6 State-of-Charge Estimation for Supercapacitors: a Kalman Filtering Formulation
- IDSP-P1.7 An Auto-Focusing Noise Suppressor for Cellphone Movies Based on Phase Randomization and Power Compensation
- IDSP-P1.8 TDA2X, A Soc Optimized For Advanced Driver Assistance Systems
- IDSP-P1.9 Anchor Free Node Tracking Using Ranges, Odometry, and Multidimensional Scaling
- IDSP-P1.10 A MATLAB-Based Magnitude Response Game for DSP Education
- IDSP-P1.11 Flipping Signals and Systems - Course Structure & Results
- IDSP-P1.12 Hands-On Real-Time DSP Teaching using Inexpensive ARM Cortex M4 Development Systems
- IDSP-P1.13 DSP See-Through: Going Beyond Talk-Through
SAM-P2: DOA Estimation
Room: Poster Area 10
Chair: Ami Wiesel (Hebrew University in Jerusalem, Israel)
- SAM-P2.1 Underdetermined DOA Estimation of Multi-path signals based on ICA and sparse reconstruction
- SAM-P2.2 Toeplitz rectification and DoA estimation with MUSIC
- SAM-P2.3 High Resolution Direction Finding from Rectangular Higher Order Cumulant Matrices: The Rectangular 2q-MUSIC Algorithms
- SAM-P2.4 DOA estimation performances of multi-parametric MUSIC in presence of modeling errors - case of coherent multi-paths
- SAM-P2.5 Nonuniform Linear Antenna Arrays for Enhanced Near Field Source Localization
- SAM-P2.6 A Computationally efficient source localization method for a mixture of Near-Field and Far-Field narrowband signals
- SAM-P2.7 ML Estimation and CRB for Narrowband AR Signals on a Sensor Array
- SAM-P2.8 DOA Estimation Exploiting Coprime Arrays with Sparse Sensor Spacing
- SAM-P2.9 A Signal Adaptive Array Interpolation Approach with Reduced Transformation Bias for DOA estimation of Highly Correlated Signals
- SAM-P2.10 Asymptotic Performance Analysis of ESPRIT-Type Algorithms for Circular and Strictly Non-circular Sources With Spatial Smoothing
- SAM-P2.11 DOA Estimation of Speech Source in Noisy Environments with Weighted Spatial Bispectrum Correlation Matrix
- SAM-P2.12 Robust DOA Estimation of Multiple Speech Sources
- SAM-P2.13 Search-Free Decentralized Direction-of-Arrival Estimation Using Common Roots for Non-Coherent Partly Calibrated Arrays
- SAM-P2.14 Single Snapshot DOA Estimation Using Compressed Sensing
10:30 AM - 11:00 AM
Coffee break
11:00 AM - 1:00 PM
SLTC-L5: Error Detection in Automatic Speech Recognition
Room: Cavaniglia
Chairs: Michiel Bacchiani (Google Inc., USA), Elmar Nöth (Universität Erlangen Nürnberg, Germany)
- 11:00 Detecting Deletions in ASR Output
- 11:20 Direct Sub-word Confidence Estimation with Hidden-state Conditional Random Fields
- 11:40 ASR Error Detection using Recurrent Neural Network Language Model and Complementary ASR
- 12:00 A Phonetic Similarity Based Noisy Channel Approach to ASR Hypothesis Re-Ranking and Error Detection
- 12:20 Exploiting un-transcribed foreign data for speech recognition in well-resourced languages
- 12:40 Close/distant talker discrimination based on kurtosis of linear prediction residual signals
SPTM-L3: Compressed Sensing II
Room: Basilica
Chairs: Mike Davies (University of Edinburgh, United Kingdom), Konstantinos Slavakis (University of Minnesota, USA)
- 11:00 Efficient Recovery of Principal Components from Compressive Measurements with Application to Gaussian Mixture Model Estimation
- 11:20 Modulated Measurement Matrix Design for Compressed Sensing
- 11:40 Lie Operators for Compressive Sensing
- 12:00 Robust Primary User Identification using Compressive Sampling for Cognitive Radios
- 12:20 the Modulated E-spline with Multiple subbands and its application to sampling wavelet-sparse signals
- 12:40 Maximum Entropy Hadamard Sensing of Sparse and Localized Signals
SS5: Seismic Signal Processing
Room: Polveriera
Chairs: Daniela Donno (MINES ParisTech, France), Renato R Lopes (University of Campinas, Brazil)
- 11:00 Seismic Signal Processing: Some Recent Advances
- 11:20 High-resolution imaging of seismic data: how to combine wave-theory with signal processing techniques
- 11:40 Fault Detection in Seismic Datasets Using Hough Transform
- 12:00 A constrained-based optimization approach for seismic data recovery problems
- 12:20 Reconstruction of signals from highly aliased multichannel samples by Generalized Matching Pursuit
- 12:40 Sparse Inversion of the Radon coefficients in the presence of erratic noise with application to simultaneous seismic source processing
MLSP-L1: Bayesian Methods
Room: Scherma
Chairs: Cédric Févotte (CNRS & Laboratoire Lagrange (CNRS, Observatoire de la Côte d'Azur & Université de Nice Sophia Antipolis), France), Dmitry Malioutov (IBM Research, USA)
- 11:00 Probabilistic 3D Mapping based on GNSS SNR Measurements
- 11:20 Learning to classify with possible sensor failures
- 11:40 Speech Decoloration based on the Product-of-Filters Model
- 12:00 Mondrian hidden Markov model for music signal processing
- 12:20 Physical Layer Authentication based on Channel Response Tracking using Gaussian Processes
- 12:40 Modeling Spatial Extremes via Ensemble-of-Trees of Pairwise Copulas
SPCOM-L2: Interference management
Room: Teatrino
Chairs: Mathini Sellathurai (Heriot-Watt University, United Kingdom), Wolfgang Utschick (Technische Universität München, Germany)
- 11:00 A Sparse MLE Approach for Joint Interference Mitigation and Data Recovery
- 11:20 Opportunistic Interference Alignment for MIMO Interfering Broadcast Channels
- 11:40 The Design of Optimal Receiver for Opportunistic Interference Alignment
- 12:00 Robust Optimization for Multi-cell Interfering MIMO-MAC under Limited Feedback
- 12:20 Partial CSI Feedback Design for Interference Alignment in MIMO Cellular Networks
- 12:40 Retrospective Interference Alignment for the 3-user MIMO Interference Channel with delayed CSIT
IVMSP-L3: Image Enhancement
Room: Volta
Chair: Gaurav Sharma (University of Rochester, USA)
- 11:00 Image Denoising by Targeted External Databases
- 11:20 Selectively Detail-enhanced Exposure Fusion via a Gradient Domain Content Adaptive Bilateral Filter
- 11:40 A New Image Filtering Method: Nonlocal Image Guided Averaging
- 12:00 Collaborative Noise Reduction using Color-Line Model
- 12:20 Epitomic Image Colorization
- 12:40 A statistical derivation of an automatic tone mapping algorithm for wide dynamic range display
SLTC-P7: Features in Speech Recognition
Room: Poster Area 1
Chair: Torbjorn Svendsen (Norwegian University of Science and Technology, Norway)
- SLTC-P7.1 MATLAB Exercises in Support of Teaching Digital Speech Processing
- SLTC-P7.2 Subband Hybrid Feature for Multi-stream Speech Recognition
- SLTC-P7.3 Music Tonality Features for Speech/Music Discrimination
- SLTC-P7.4 A Pitch Extraction Algorithm Tuned For Automatic Speech Recognition
- SLTC-P7.5 Multi-view learning with supervision for transformed bottleneck features
- SLTC-P7.6 Joint noise adaptive training for robust automatic speech recognition
- SLTC-P7.7 Analysis-by-synthesis feature estimation for robust automatic speech recognition using spectral masks
- SLTC-P7.8 A Discriminatively Trained Hough Transform for Frame-Level Phoneme Recognition
- SLTC-P7.9 Analyzing Convolutional Neural Networks for Speech Activity Detection in Mismatched Acoustic Conditions
- SLTC-P7.10 Learning Dynamic Features with Neural Networks for Phoneme Recognition
- SLTC-P7.11 Contrastive Auto-encoder for Phoneme Recognition
- SLTC-P7.12 Transductive Nonnegative Matrix Factorization for Semi-Supervised High-Performance Speech Separation
- SLTC-P7.13 Automatic phonetic segmentation in Mandarin Chinese: boundary models, glottal features and tone
- SLTC-P7.14 UT-VOCAL EFFORT II: Analysis and Constrained-Lexicon Recognition of Whispered Speech
SLTC-P8: Statistical speech synthesis
Room: Poster Area 2
Chair: Tomoki Toda (NAIST, Japan)
- SLTC-P8.1 Tongue shape conversion with non-parallel training data
- SLTC-P8.2 Dialogue Context Sensitive HMM-Based Speech Synthesis
- SLTC-P8.3 Integration of speaker and pitch adaptive training for HMM-based singing voice synthesis
- SLTC-P8.4 Parametric Representation for Singing Voice Synthesis: A Comparative Evaluation
- SLTC-P8.5 Very Fast Unit Selection Using Viterbi Search with Zero-Concatenation-Cost Chains
- SLTC-P8.6 Speaker dependent expression predictor from text: expressiveness and transplantation
- SLTC-P8.7 Fundamental Frequency Generation for Whisper-to-Audible Speech Conversion
- SLTC-P8.8 A novel pitch decomposition method for the Generalized Linear Alignment Model
- SLTC-P8.9 Narrow Adaptive Regularization of Weights for Grapheme-to-Phoneme Conversion
- SLTC-P8.10 Automatic Discovery of a Phonetic Inventory for unwritten languages for statistical speech synthesis
- SLTC-P8.11 Neural net word representations for phrase-break prediction without a part of speech tagger
SPTM-P7: Digital and Multirate Signal Processing
Room: Poster Area 3
Chair: P. p. Vaidyanathan (Cal Tech., USA)
- SPTM-P7.1 M-Channel Oversampled Perfect Reconstruction Filter Banks for Graph Signals
- SPTM-P7.2 Mixer sequence design for N-path filters
- SPTM-P7.3 Fractional Number-Theoretic Transforms Based on Matrix Functions
- SPTM-P7.4 Lifting Wavelet Design by Block Wavelet Transform Inversion
- SPTM-P7.5 Structured Dictionary Learning with 2-D Non-separable Oversampled Lapped Transform
- SPTM-P7.6 FFT based solution for multivariable l2 equations using KKT system via FFT and efficient pixel-wise inverse calculation
- SPTM-P7.7 Frequency domain linear prediction based on temporal analysis
- SPTM-P7.8 An efficient 18-band quasi-ANSI 1/3-octave filter bank using re-sampling method for digital hearing aids
- SPTM-P7.9 On the Choice of Window for Spatial Smoothing of Spherical Data
- SPTM-P7.10 Multi-wavelet coherence for point processes on the real line
IFS-P1: Multimedia Forensics
Room: Poster Area 4
Chair: Marco Tagliasacchi (Politecnico di Milano, Italy)
- IFS-P1.1 Image Tampering Detection By Exposing Blur Type Inconsistency
- IFS-P1.2 Demosaicing Strategy Identification Via Eigen Algorithms
- IFS-P1.3 Exploiting perceptual quality issues in countering sift-based forensic methods
- IFS-P1.4 Detecting double compressed AMR audio using deep learning
- IFS-P1.5 Exposing Video Inter-frame Forgery base on Velocity Field Consistency
- IFS-P1.6 Wireless Device Identification Based on RF Oscillator Imperfections
- IFS-P1.7 High Dimensional Changepoint Detection with a Dynamic Graphical Lasso
- IFS-P1.8 Information Theoretical Limit of Compression Forensics
- IFS-P1.9 SOFIR: Securely Outsourced Forensic Image Recognition
- IFS-P1.10 Transportation-theoretic image counterforensics to first significant digit histogram forensics
- IFS-P1.11 Countering Anti-Forensics of Median Filtering
- IFS-P1.12 Antiforensic synthesis of motion vectors using template algorithms
SPCOM-P4: Relaying
Room: Poster Area 5
Chair: Antti Tölli (University of Oulu, Finland)
- SPCOM-P4.1 Multi-Group Multi-way Relaying with Reduced Number of Relay Antennas
- SPCOM-P4.2 Robust Transmit Design for Secure AF Relay Networks Based on Worst-Case Optimization
- SPCOM-P4.3 An amplify-and-forward scheme for cognitive radios
- SPCOM-P4.4 Geometric Monitoring for CSI Reduction in Amplify-and-Forward Relay Networks
- SPCOM-P4.5 Robust Beamforming in Two-Way Relay Networks: Quartically Perturbed Chance Constrained Formulation and Tractable Approximation
- SPCOM-P4.6 Simplified MIMO Relay Design for Multicasting from Multiple-Sources
- SPCOM-P4.7 A Parametric Approach to Optimal Soft Signal Relaying in Wireless Parallel-Relay Systems
- SPCOM-P4.8 Power Control for Achieving Energy-Efficient Multiuser Two-Way Balancing Relay Networks
- SPCOM-P4.9 Joint parallel interference cancellation and relay selection algorithms based on greedy techniques for cooperative DS-CDMA systems
- SPCOM-P4.10 Effect of Phase Noise on Digital Self-Interference Cancellation in Wireless Full Duplex
- SPCOM-P4.11 Sampling Jitter in Full-Duplex Radio Transceivers: Estimation and Mitigation
- SPCOM-P4.12 Feasibility Study on Full-Duplex Wireless Millimeter-Wave Systems
IVMSP-P6: Image Analysis I
Room: Poster Area 6
Chair: Kenneth Lam (Hong Kong Polytechnic University, Hong Kong)
- IVMSP-P6.1 Removal of bleed-through effect via nonnegative least-correlation
- IVMSP-P6.2 Thermal-Image Quality Measurements
- IVMSP-P6.3 A Perceptual Blind Blur Image Quality Metric
- IVMSP-P6.4 A Statistical Evaluation of Sparsity-based Distance Measure (SDM) as an Image Quality Assessment Algorithm
- IVMSP-P6.5 Objective Similarity Metrics for Scenic Bilevel Images
- IVMSP-P6.6 Saliency Detection based on Extended Boundary Prior with Foci of attention
- IVMSP-P6.7 Segmentation-enhanced Saliency Detection Model Based on Distance Transform and Center Bias
- IVMSP-P6.8 From Quaternion to Octonion: Feature-based Image Saliency Detection
- IVMSP-P6.9 Co-Saliency Detection Based on Hierarchical Segmentation
- IVMSP-P6.10 Retargeting Pyramid Using Direct Decimation
- IVMSP-P6.11 A computing method of double linear correlation for mirror image matching
- IVMSP-P6.12 Multiscale Anomaly Detection Using Diffusion Maps and Saliency Score
BISP-P2: Biomedical Informatics and Image Analysis II
Room: Poster Area 7
Chair: Jean-Christophe Olivo-Marin (Institut Pasteur, France)
- BISP-P2.1 Structured sparse PCA to identify miRNA co-regulatory modules
- BISP-P2.2 Variable selection for noisy data applied in proteomics
- BISP-P2.3 Fast Spatially Variant Deconvolution for Optical Microscopy via Iterative Shrinkage Thresholding
- BISP-P2.4 A Comparison of x-lets in Denoising cDNA Microarray Images
- BISP-P2.5 Generalized Extreme Value Distributions, Information Geometry and Sharpness Functions for Microscopy Images
- BISP-P2.6 Classification of Temporal Gene Expression Data Using Wavelet Domain Feature in Kernel SVM
- BISP-P2.7 Quantitative control of the error bounds of a fast super-resolution technique for microscopy and astronomy
AASP-P4: Spatial Audio I, Signal Enhancement I
Room: Poster Area 8
Chair: John Hershey (MERL, USA)
- AASP-P4.1 Gaussian Process Models for HRTF based 3D Sound Localization
- AASP-P4.2 Large Deformation Diffeomorphic Metric Mapping and Fast-Multipole Boundary Element Method provide new insights for Binaural Acoustics
- AASP-P4.3 A Study on the Frequency-Domain Primary-Ambient Extraction for Stereo Audio Signals
- AASP-P4.4 The Influence of Low Order Reflections on the Interaural Time Differences in Crosstalk Cancellation Systems
- AASP-P4.5 Down-Mixing Using Coherence Suppression
- AASP-P4.6 Coupled Dictionary Training for Exemplar-based Speech Enhancement
- AASP-P4.7 Localization of Impulsive Disturbances in Archive Audio Signals Using Predictive Matched Filtering
- AASP-P4.8 Employing Phase Information for Audio Denoising
- AASP-P4.9 Sparse Denoising of Audio by Greedy Time-Frequency Shrinkage
- AASP-P4.10 Single-channel speech presence probability estimation using inter-frame and inter-band correlations
MLSP-P1: Pattern Recognition and Classification
Room: Poster Area 9
Chair: Konstantinos Diamantaras (TEI of Thessaloniki, Greece)
- MLSP-P1.1 A network of cooperative learners for data-driven stream mining
- MLSP-P1.2 Parsimonious Gaussian process models for the classification of multivariate remote sensing images
- MLSP-P1.3 Real-Time Action Recognition Based on Cumulative Motion Shapes
- MLSP-P1.4 Conformal Predictors for Online Track Classification
- MLSP-P1.5 Training ensemble of diverse classifiers on feature subsets
- MLSP-P1.6 Splitting-While-Merging Framework for Clustering High-Dimension Data with Component-Wise Expectation Conditional Maximisation
- MLSP-P1.7 K-mappings and regression trees
- MLSP-P1.8 Semi-Supervised Learning Using a Graph-based Phase Field Model for Imbalanced Data Set Classification
- MLSP-P1.9 Sensing-aware kernel SVM
- MLSP-P1.10 Fast Margin-based Cost-Sensitive Classification
- MLSP-P1.11 Recycled Linear Classifiers for Multiclass Classification
SAM-P3: Detection and Estimation
Room: Poster Area 10
Chair: Jean Pierre Delmas (UMR CNRS 5157 - CITI Department, France)
- SAM-P3.1 Bayesian Cramer-Rao Type Bound for Risk-Unbiased Estimation With Deterministic Nuisance Parameters
- SAM-P3.2 Estimating the number of signals in the presence of nonuniform noise
- SAM-P3.3 Joint Angle and Frequency Estimation Using Structured Least Squares
- SAM-P3.4 Time delay estimation in the presence of clock frequency error
- SAM-P3.5 Joint Frequency and Phasor Estimation in Unbalanced Three-Phase Power Systems
- SAM-P3.6 Multichannel Detection of an Unknown Rank-One Signal with Uncalibrated Receivers
- SAM-P3.7 Fourth-Order Tensor Method for Blind Spatial Signature Estimation
- SAM-P3.8 Conditional Cramér-Rao Lower Bounds for DOA Estimation and Array Calibration
- SAM-P3.9 Sparse Array-Based Room Transfer Function Estimation for Echo Cancellation
- SAM-P3.10 Random Distributed Detection with an application to Cognitive Radio Byzantine Attack
- SAM-P3.11 Detection of Correlated Time Series in a Network of Sensor Arrays
- SAM-P3.12 A Low Power Self-capacitive Touch Sensing Analog Front End with Sparse Multi-touch Detection
- SAM-P3.13 Blind Beamforming Techniques for Automatic Identification System using GSVD and Tracking
1:00 PM - 2:30 PM
Lunch Time
2:30 PM - 2:45 PM
Opportunities for International Research Support through the US Office of Naval Research-Global (ONRG)
Leonard Ferrari (U.S. Office of Naval Research Global-London)
2:45 PM - 3:45 PM
PT2: Plenary Talk: Model-Based Signal Processing (Room Cavaniglia)
Keynote speaker: Chris Bishop (Microsoft Research Cambridge, UK)
3:45 PM - 4:15 PM
Coffee break
4:15 PM - 6:15 PM
SLTC-L6: Articulatory features in speech processing
Room: Cavaniglia
Chairs: John Hansen (University of Texas at Dallas, USA), Sabato M Siniscalchi (University of Enna Kore, Italy)
- 4:15 Articulatory features from deep neural networks and their role in speech recognition
- 4:35 Refinements of Regression-based Context-Dependent Modelling of Deep Neural Networks for Automatic Speech Recognition
- 4:55 Normalization of articulatory data through Procrustes transformations and analysis-by-synthesis
- 5:15 A sparse smoothing approach for Gaussian mixture model based acoustic-to-articulatory inversion
- 5:35 The Effect of Speaking Rate on Audio and Visual Speech
- 5:55 Trajectory Analysis of Speech using Continuous State Hidden Markov Models
SPTM-L4: Classification and Pattern Recognition
Room: Basilica
Chairs: Prakash Ishwar (Boston University, USA), Todd Moon (Utah State University, USA)
- 4:15 Improvement of utterance clustering by using employees' sound and area data
- 4:35 Acoustic Feature Extraction By Statistics Based Local Binary Pattern For Environmental Sound Classification
- 4:55 Spectral Clustering with Imbalanced Data
- 5:15 Subspace Learning in Minimax Detection
- 5:35 Information-Theoretic Criteria for the Design of Compressive Subspace Classifiers
- 5:55 Sparse Adaptive Possibilistic Clustering
SS6: Dictionary-based processing of single- and multi-channel audio
Room: Polveriera
Chairs: Peter Balazs (Austrian Academy of Sciences, Austria), Marco Liuni (IRCAM, France)
- 4:15 A General Framework For Dictionary Based Audio Fingerprinting
- 4:35 Online Non-negative Tensor Deconvolution for Source Detection in 3DTV Audio
- 4:55 Hearing behind walls: localizing sources in the room next door with cosparsity
- 5:15 Active-set Newton algorithm for non-negative sparse coding of audio
- 5:35 Adaptive Gabor Frames by Projection onto Time-Frequency Subspaces
- 5:55 Perceptual Matching Pursuit with Gabor dictionaries and time-frequency masking
AASP-L3: Music Transcription
Room: Scherma
Chairs: Bryan Pardo (Northwestern University, USA), Emmanuel Vincent (Inria Nancy - Grand Est, France)
- 4:15 Automatic transcription of pitched and unpitched sounds from polyphonic music
- 4:35 Polyphonic Piano Transcription using Non-negative matrix factorisation and group sparsity
- 4:55 Leveraging Repetition for Improved Automatic Lyric Transcription in popular music
- 5:15 Automatic Transcription of Guitar Tablature from Audio Signals in Accordance with Player's Proficiency
- 5:35 Transcribing Vocal Expression from Polyphonic Music
- 5:55 Enhancing downbeat estimation when facing different music styles
SPCOM-L3: Massive MIMO
Room: Teatrino
Chairs: Timothy N. Davidson (McMaster University, Canada), Erik G. Larsson (Linköping University, Sweden)
- 4:15 Antenna Subset Selection Optimization for Large-scale MISO Constant Envelope Precoding
- 4:35 Massive MIMO Systems with Hardware-Constrained Base Stations
- 4:55 Constant Envelope Signal Space Diversity
- 5:15 Multi-Stream Iterative SVD for Massive MIMO Communication Systems under Time Varying Channels
- 5:35 CSIT Estimation and Feedback for FDD Multi-user Massive MIMO Systems
- 5:55 Uplink Performance of Massive MIMO Subject to Delayed CSIT and Anticipated Channel Prediction
SAM-L2: Hyperspectral Processing and Source Separation
Room: Volta
Chairs: Chong-Yung Chi (National Tsing Hua University, Taiwan), Dominic K. C. Ho (University of Missouri, USA)
- 4:15 Residual Component Analysis of Hyperspectral Images for Joint Nonlinear Unmixing and Nonlinearity Detection
- 4:35 Blind spatial unmixing of multispectral images: an approach based on two-source sparsity and geometrical properties
- 4:55 Bayesian fusion of hyperspectral and multispectral images
- 5:15 Synthetic Coded Apertures in Compressive Spectral Imaging
- 5:35 Error Analysis of Low-Rank Three-Way Tensor Factorization Approach to Blind Source Separation
- 5:55 Underdetermined blind separation and tracking of moving sources based on DOA-HMM
SLTC-P9: Spoken Language Processing
Room: Poster Area 1
Chair: Florian Metze (Carnegie Mellon University, USA)
- SLTC-P9.1 Sensorimotor adaptation of speech using real-time articulatory resynthesis
- SLTC-P9.2 Learning a semantic parser from spoken utterances
- SLTC-P9.3 A DNN-based Acoustic Modeling of Tonal Language and Its Application to Mandarin Pronunciation Training
- SLTC-P9.4 Spoken Dialogue Grammar Induction from Crowdsourced Data
- SLTC-P9.5 Improved and robust prediction of pronunciation distance for individual-basis clustering of World Englishes pronunciation
- SLTC-P9.6 Ordinal Regression for Interaction Quality Prediction
- SLTC-P9.7 Effective Pseudo-relevance Feedback for Language Modeling in Extractive Speech Summarization
- SLTC-P9.8 Some Insights from Translating Conversational Telephone Speech
- SLTC-P9.9 Gaze-enhanced speech recognition
- SLTC-P9.10 Computationally-efficient endpointing features for natural spoken interaction with personal-assistant systems
- SLTC-P9.11 Task specific continuous word representations for mono and multi-lingual Spoken Language Understanding
- SLTC-P9.12 Factored Adaptation of Speaker and Environment Using Orthogonal Subspace Transforms
- SLTC-P9.13 Black box optimization for automatic speech recognition
SLTC-P10: Large-Vocabulary Continuous Speech Recognition
Room: Poster Area 2
Chair: Brian Mak (The Hong Kong University of Science and Technology, Hong Kong)
- SLTC-P10.1 Gradient-Free Decoding Parameter Optimization on Automatic Speech Recognition
- SLTC-P10.2 Stochastic Pooling Maxout Networks for Low-Resource Speech Recognition
- SLTC-P10.3 Accurate client-server based speech recognition keeping personal data on the client
- SLTC-P10.4 Progress in Dynamic Network Decoding
- SLTC-P10.5 RASR/NN: The RWTH Neural Network Toolkit For Speech Recognition
- SLTC-P10.6 The RWTH English lecture recognition system
- SLTC-P10.7 Accelerating Large Vocabulary Continuous Speech Recognition on Heterogeneous CPU-GPU Platforms
- SLTC-P10.8 Multi-Stream Combination for LVCSR and Keyword Search on GPU-Accelerated Platform
- SLTC-P10.9 Chasing The Metric: Smoothing Learning Algorithms For Keyword Detection
- SLTC-P10.10 Barista: A Framework for Concurrent Speech Processing by USC-SAIL
- SLTC-P10.11 Submodular Subset Selection for Large-Scale Speech Training Data
- SLTC-P10.12 Training Data Selection Based on Context-Dependent State Matching
- SLTC-P10.13 Infinite Structured Support Vector Machines for Speech Recognition
- SLTC-P10.14 Attribute based lattice rescoring in spontaneous speech recognition
SPTM-P8: Compressed Sensing III
Room: Poster Area 3
Chair: Rémi Gribonval (INRIA, France)
- SPTM-P8.1 Side Information-Aided Compressed Sensing Reconstruction via Approximate Message Passing
- SPTM-P8.2 Poisson Group Testing: A Probabilistic Model for Nonadaptive Streaming Boolean Compressed Sensing
- SPTM-P8.3 Compressed Sensing Reconstruction of Convolved Sparse Signals
- SPTM-P8.4 Exploiting the Convex-Concave Penalty for Tracking: A Novel Dynamic Reweighted Sparse Bayesian Learning Algorithm
- SPTM-P8.5 The Convergence Guarantees of a Non-convex Approach for Sparse Recovery Using Regularized Least Squares
- SPTM-P8.6 Robust Off-Grid Recovery from Compressed Measurements
- SPTM-P8.7 Screening for Learning Classification Rules via Boolean Compressed Sensing
- SPTM-P8.8 Decentralized subspace pursuit for joint sparsity pattern recovery
- SPTM-P8.9 On the Theoretical Analysis of Cross Validation in Compressive Sensing
- SPTM-P8.10 Complex Multitask Bayesian Compressive sensing
- SPTM-P8.11 Comparing multivariate complex random signals: Performance analysis and application
- SPTM-P8.12 Gridless Compressive Sensing
- SPTM-P8.13 Revisiting Robustness of the Union-of-Subspaces Model for Data-Adaptive Learning of Nonlinear Signal Models
- SPTM-P8.14 Reconstruction of sparse signals from highly corrupted measurements by nonconvex minimization
SPTM-P9: Detection
Room: Poster Area 4
Chair: Hamid Krim (North Carolina State University, USA)
- SPTM-P9.1 Detecting Edges of Reflections from a Single Image via Convex Optimization
- SPTM-P9.2 Compressed Change Detection
- SPTM-P9.3 Distributed Vector Decorrelation and Anomaly Detection Using The Vector Sparse Matrix Transform
- SPTM-P9.4 An asymptotic GLRT for the detection of cyclostationary signals
- SPTM-P9.5 Multiple Testing for Sequential Probability Ratio Tests with Application to Multiband Spectrum Sensing
- SPTM-P9.6 Spectral Subgraph Detection with Corrupt Observations
- SPTM-P9.7 On the Epsilon-Optimal Discrimination of Two One-Dimensional Subspaces
- SPTM-P9.8 Bayesian Network Detection Using Absorbing Markov Chains
- SPTM-P9.9 A New Unsupervised Threshold Determination For Hybrid Models
- SPTM-P9.10 Real Time Detection of Harmonic Structure: A Case For Topological Signal Analysis
- SPTM-P9.11 Power System Line Outage Detection and Identification---A Quickest Change Detection Approach
- SPTM-P9.12 Designing Discrete Sequential Tests via Mixed Integer Programming
- SPTM-P9.13 Digital Modulation Recognition Using Circular Harmonic Approximation of Likelihood Function
- SPTM-P9.14 Robust Testing for Stationarity in the Presence of Outliers
SPCOM-P5: Transmitter design
Room: Poster Area 5
Chair: Sergiy A. Vorobyov (Aalto University & University of Alberta on leave, Finland)
- SPCOM-P5.1 Delay Control For CDF Scheduling Using Markov Decision Process
- SPCOM-P5.2 QoS Feasibility in MIMO Broadcast Channels With Widely Linear Transceivers
- SPCOM-P5.3 Optimality of Proper Signaling in Gaussian MIMO Broadcast Channels with Shaping Constraints
- SPCOM-P5.4 Distributionally Robust Chance-Constrained Transmit Beamforming for Multiuser MISO Downlink
- SPCOM-P5.5 On the Complexity of SINR Outage Constrained Max-Min-Fairness Multicell Coordinated Beamforming Problem
- SPCOM-P5.6 Predictive quantization of bit loading for MIMO Time-Correlated Channels with Limited Feedback
- SPCOM-P5.7 Transmission Power Variance Constrained Power Allocation for Iterative Frequency Domain Multiuser SIMO Detector
- SPCOM-P5.8 Hyperbolic Frequency Modulation for Multiple Users in Underwater Acoustic Communications
- SPCOM-P5.9 Optimal Channel Switching For Average Capacity Maximization
- SPCOM-P5.10 Green Resource Allocation in Relay-Assisted MIMO Systems with Statistical Channel State Information
- SPCOM-P5.11 Energy Beamforming with One-Bit Feedback
- SPCOM-P5.12 Sum-Rate Maximization for Active Channels
- SPCOM-P5.13 Finite-Horizon Optimal Transmission Policies for Energy Harvesting Sensors
IVMSP-P7: Sparse coding and Dictionary Learning
Room: Poster Area 6
Chair: Christian Jutten (GIPSA-Lab, France)
- IVMSP-P7.1 Super-resolution Mapping via Multi-dictionary based Sparse Representation
- IVMSP-P7.2 BSIK-SVD: A Dictionary-Learning Algorithm for Block-Sparse Representations
- IVMSP-P7.3 Structured sparse coding for image denoising or pattern detection
- IVMSP-P7.4 Violent Video Detection Based on MoSIFT Feature and Sparse Coding
- IVMSP-P7.5 Task-driven dictionary learning for inpainting
- IVMSP-P7.6 Sparse Localized Facial Motion Dictionary Learning for Facial Expression Recognition
- IVMSP-P7.7 Sparse Reconstruction for Disparity Maps using Combined Wavelet and Contourlet Transforms
- IVMSP-P7.8 Learning Semantic Kernels For Scene Classification
- IVMSP-P7.9 Transformation-invariant dictionary learning for classification with 1-sparse representations
- IVMSP-P7.10 An Adaptive Dictionary Learning Approach for Modeling Dynamical Textures
- IVMSP-P7.11 Laplacian Tensor Sparse Coding for image Categorization
- IVMSP-P7.12 Iterative Directional Total Variation Refinement for Compressive Sensing Image Reconstruction
- IVMSP-P7.13 Dictionary Learning for Sparse Representation: A Novel Approach
BISP-P3: Computer-aided diagnosis and intervention
Room: Poster Area 7
Chair: Gloria Menegaz (University of Verona, Italy)
- BISP-P3.1 Subject Independent Identification of Breath Sounds Components Using Multiple Classifiers
- BISP-P3.2 Multiscale Sample Entropy for Time Resolved Epileptic Seizure Detection and Fingerprinting
- BISP-P3.3 The Development of a Multi-stage Learning Scheme Using New Tissue Descriptors for Automatic Grading of Prostatic Carcinoma
- BISP-P3.4 Background noise classification using random forest tree classifier for cochlear implant applications
- BISP-P3.5 Advanced Algorithms for Surgical Gesture Classification
- BISP-P3.6 A Pattern Recognition Approach Based on Electrodermal Response for Pathological Mood Identification in Bipolar Disorders
- BISP-P3.7 A Novel Method for Obstructive Sleep Apnea Severity Estimation Using Speech Signals
- BISP-P3.8 Color Identification in Dermoscopy Images using Gaussian Mixture Models
- BISP-P3.9 An Investigation of Relationship between Bone Vibration Frequency and its Mass-Volume Ratio
- BISP-P3.10 Nearest-Manifold Classification Approach for Cardiac Arrest Rhythm Interpretation during Resuscitation
- BISP-P3.11 Randomized Stimulation Signal Design to Create Partial Informational Lesions in Parkinsonian Neuronal Networks
- BISP-P3.12 Context-Based Signal Descriptors of Heart-Rate Variability for Anxiety Assessment
- BISP-P3.13 Multi-Modal Prediction of PTSD and Stress Indicators
- BISP-P3.14 High accuracy discrimination of Parkinson's disease participants from healthy controls using smartphones
AASP-P5: Hearing Aids I, Audio Coding
Room: Poster Area 8
Chair: Tao Zhang (Starkey Hearing Technologies, USA)
- AASP-P5.1 Closed-loop feedback cancellation utilizing two microphones and transform domain processing
- AASP-P5.2 Design of a High Order Binaural Microphone Array For Hearing Aids Using a Rigid Spherical Model
- AASP-P5.3 Robust Wind Noise Detection
- AASP-P5.4 Perceptually motivated coherence preservation in multi-channel Wiener filtering based noise reduction for binaural hearing aids
- AASP-P5.5 Modeling the common part of acoustic feedback paths in hearing aids using a pole-zero model
- AASP-P5.6 A spatial priority based scalable audio coding
- AASP-P5.7 New Bit-Plane Probability Calculations for Scalable to Lossless Audio Coding
- AASP-P5.8 On Relaxing the Strict Hierarchical Constraints in Layered Coding of Audio Signals
- AASP-P5.9 Error resilience enhancement for a robust ADPCM audio coding scheme
- AASP-P5.10 On Noise Propagation in Closed-Loop Linear Predictive Coding
- AASP-P5.11 Superwideband Extension for AMR-WB using Conditional Codebook
MLSP-P2: Machine Learning for Audio and Speech
Room: Poster Area 9
Chair: Paris Smaragdis (University of Illinois at Urbana-Champaign, USA)
- MLSP-P2.1 Modeling Speech with Sum-Product Networks: Application to Bandwidth Extension
- MLSP-P2.2 A Bag-of-Features Approach to Acoustic Event Detection
- MLSP-P2.3 Single-Channel Speech Separation With Memory-Enhanced Recurrent Neural Networks
- MLSP-P2.4 Mixture of Gaussian process experts for predicting sung melodic contour with expressive dynamic fluctuations
- MLSP-P2.5 Pattern Discovery in Continuous Speech Using Block Diagonal Infinite HMM
- MLSP-P2.6 Emotion Detection in Speech using Deep Networks
- MLSP-P2.7 CCA Based Feature Selection with Application to Continuous Depression Recognition from Acoustic Speech Features
- MLSP-P2.8 Deep Neural Networks For Single Channel Source Separation
- MLSP-P2.9 Kernel-Based Identification of Hammerstein Systems for Nonlinear Acoustic Echo-Cancellation
- MLSP-P2.10 Intelligibility Detection of Pathological Speech Using Asymmetric Sparse Kernel Partial Least Squares Classifier
- MLSP-P2.11 Discriminative Non-Negative Matrix Factorization for Single-Channel Speech Separation
- MLSP-P2.12 Block Sparse Excitation Based All-Pole Modeling of Speech
IFS-P2: Biometrics and Content Fingerprinting
Room: Poster Area 10
Chair: Patrizio Campisi (University of ROMA TRE, Italy)
- IFS-P2.1 Iris Template Protection Using a Digital Modulation Paradigm
- IFS-P2.2 Heterogeneous Iris Recognition using Heterogeneous Eigeniris and Sparse Representation
- IFS-P2.3 Verification based ECG biometrics with cardiac irregular conditions using heartbeat level and segment level information fusion
- IFS-P2.4 On Establishing Evaluation Standards for ECG Biometrics
- IFS-P2.5 Performance of i-Vector Speaker Verification and the Detection of Synthetic Speech
- IFS-P2.6 Human Acoustic Fingerprints: A Novel Biometric Modality for Mobile Security
- IFS-P2.7 An HMM-based Behavior Modeling Approach for Continuous Mobile Authentication
- IFS-P2.8 Robust Perceptual Color Image Hashing Using Quaternion Singular Value Decomposition
- IFS-P2.9 Performance analysis of bag-of-features based content identification systems
- IFS-P2.10 Fast and Accurate Nearest Neighbor Search in the Manifolds of Symmetric Positive Definite Matrices
- IFS-P2.11 Fingerprint Information Maximization for Content Identification
- IFS-P2.12 Efficient two stage decoding scheme to achieve content identification capacity
Thursday, May 8
8:30 AM - 10:30 AM
SLTC-L7: Parametric Speech Synthesis
Room: Cavaniglia
Chairs: Alan Black (CMU, USA), Zhen-Hua Ling (University of Science and Technology of China, P.R. China)
- 8:30 Decision Tree Usage for Incremental Parametric Speech Synthesis
- 8:50 Spectral Modeling Using Neural Autoregressive Distribution Estimators for Statistical Parametric Speech Synthesis
- 9:10 On the Training Aspects of Deep Neural Network (DNN) for Parametric TTS Synthesis
- 9:30 Parametric Speech Synthesis Based on Gaussian Process Regression Using Global Variance and Hyperparameter Optimization
- 9:50 Complex cepstrum factorization for statistical parametric synthesis
- 10:10 Deep Mixture Density Networks for Acoustic Modeling in Statistical Parametric Speech Synthesis
SPTM-L5: Signal Processing over Graphs II
Room: Basilica
Chairs: Alfred Hero III (University of Michigan, USA), Ali H. Sayed (University of California, Los Angeles, USA)
- 8:30 On lq Estimation of Sparse Inverse Covariance
- 8:50 Anomalous Cluster Detection
- 9:10 A Stable Betweenness Centrality Measure in Networks
- 9:30 Towards a sampling theorem for signals on arbitrary graphs
- 9:50 On the Convergence Rate of the Bi-Alternating Direction Method of Multipliers
- 10:10 Online Dictionary Learning over Distributed Models
DISPS-L1: Algorithm and Architecture Co-Optimization
Room: Polveriera
Chairs: Magdy Bayoumi (University of Louisiana, USA), Warren Gross (McGill University, Canada)
- 8:30 A 3.8 Gb/s Large-scale MIMO Detector for 3GPP LTE-Advanced
- 8:50 Error-Adaptive Classifier Boosting (EACB): Exploiting Data-driven Training for Highly Fault-tolerant Hardware
- 9:10 Design and Implementation of a Low Power Spike Detection Processor for 128-Channel Spike Sorting Microsystem
- 9:30 Towards Approaching near-Optimal MIMO detection performance on a C-programmable baseband processor
- 9:50 FFTs with Near-Optimal Memory Access Through Block Data Layouts
- 10:10 LLR-Based Successive Cancellation List Decoding of Polar Codes
SS7: Joint Optimization of RF devices and Resource Allocation in Wireless Networks
Room: Scherma
Chairs: Erik G. Larsson (Linköping University, Sweden), Jarmo Takala (Tampere University of Technology, Finland)
- 8:30 Reduced-Complexity Power Amplifier Linearization for Carrier Aggregation Mobile Transceivers
- 8:50 Multiuser Frequency Allocation with Wideband Power Amplifier Models
- 9:10 Digital predistortion of concurrent multiband communication systems
- 9:30 Iterative Blind Estimation of Nonlinear Channels
- 9:50 Cross Layer Energy-Efficiency Optimization for Cognitive Radio Transceivers
- 10:10 Efficient Architecture Mapping of FFT/IFFT for Cognitive Radio Networks
SAM-L3: Sparsity Structures
Room: Teatrino
Chairs: Yonina C. Eldar (Technion-Israel Institute of Technology, Israel), Geert Leus (Delft University of Technology, The Netherlands)
- 8:30 Joint Sparsity Recovery for Spectral Compressed Sensing
- 8:50 Sparse Reconstruction Of Equivalence Classes Of Moving Targets Using Single-Channel Synthetic Aperture Radar
- 9:10 Sparsity-Aware Field Estimation via Ordinary Kriging
- 9:30 A block-sparse MUSIC algorithm for the localization and the identification of directive sources
- 9:50 Joint DOA and Multi-pitch estimation using Block Sparsity
- 10:10 Tensor-Based Algorithms for Learning Multidimensional Separable Dictionaries
IFS-L1: Secret Communications, Fingerprinting, and Security
Room: Volta
Chairs: Oscar C. Au (HKUST, Hong Kong), Yao-Win Peter Hong (National Tsing Hua University, Taiwan)
- 8:30 Artificial-Noise-Aided Secure Multi-Antenna Transmission in Slow Fading Channels with Limited Feedback
- 8:50 Strong Secrecy and Decoding Performance Analysis for Robust Broadcasting Under Channel Uncertainty
- 9:10 On the Performance of Full-Duplex Relaying under PHY Security Constraints
- 9:30 Steganalysis in Technicolor: Boosting WS Detection of Stego Images from CFA-Interpolated Covers
- 9:50 TTP-Free Asymmetric Fingerprinting Protocol based on Client Side Embedding
- 10:10 On the Security of Random Linear Measurements
SLTC-P11: Features for Speaker Recognition
Room: Poster Area 1
Chair: Panayiotis Georgiou (University of Southern California, USA)
- SLTC-P11.1 Robust speaker identification in noisy and reverberant conditions
- SLTC-P11.2 Inter Dataset Variability Compensation for Speaker Recognition
- SLTC-P11.3 Minimum Divergence Estimation of Speaker Prior in Multi-Session PLDA Scoring
- SLTC-P11.4 Construction of Discriminative Kernels from Known and Unknown Non-targets for PLDA-SVM Scoring
- SLTC-P11.5 Uncertainty Propagation in Front End Factor Analysis For Noise Robust Speaker Recognition
- SLTC-P11.6 Frequency offset correction in single sideband speech for speaker verification
- SLTC-P11.7 Effective Use of DCTs for Contextualizing Features for Speaker Recognition
- SLTC-P11.8 Domain Adaptation via Within-Class Covariance Correction in i-vector Based Speaker Recognition Systems
- SLTC-P11.9 Simplified VTS-based i-vector Extraction in Noise-robust Speaker Recognition
- SLTC-P11.10 Unscented Transform for iVector-Based Noisy Speaker Recognition
- SLTC-P11.11 Supervised Domain Adaptation for i-vector based Speaker Recognition
- SLTC-P11.12 Deep Neural Networks for Small Footprint Text-Dependent Speaker Verification
- SLTC-P11.13 Iterative Bayesian Word Segmentation for Unsupervised Vocabulary Discovery from Phoneme Lattices
SLTC-P12: Spoken Language Understanding II
Room: Poster Area 2
Chair: Larry Heck (Microsoft Research, USA)
- SLTC-P12.1 unsupervised broadcast news story segmentation using distance dependent Chinese restaurant processes
- SLTC-P12.2 Extending Domain Coverage of Language Understanding Systems via Intent Transfer Between Domains Using Knowledge Graphs and Search Query Click Logs
- SLTC-P12.3 A Variational Bayesian Model for User Intent Detection
- SLTC-P12.4 Recurrent Conditional Random Field for Language Understanding
- SLTC-P12.5 Leveraging Semantic Web Search and Browse Sessions for Multi-Turn Spoken Dialog Systems
- SLTC-P12.6 Small-Footprint Keyword Spotting Using Deep Neural Networks
- SLTC-P12.7 Log-Linear Dialog Manager
- SLTC-P12.8 Retrieving the syntactic structure of erroneous ASR transcriptions for open-domain Spoken Language Understanding
- SLTC-P12.9 Language Model Adaptation For Automatic Call Transcription
- SLTC-P12.10 Unsupervised Submodular Subset Selection for Speech Data
- SLTC-P12.11 A Submodular Optimization Approach to Sentence Set Selection
- SLTC-P12.12 Semantic Context Inference for Spoken Document Retrieval using Term Association Matrices
- SLTC-P12.13 Strategies For Vietnamese Keyword Search
SPTM-P10: Signal Sampling, Sensing and Reconstruction I
Room: Poster Area 3
Chair: Geert Leus (Delft University of Technology, The Netherlands)
- SPTM-P10.1 A Sub-Band Based Reconstructor for M-Channel Time-Interleaved ADCs with Missing Samples
- SPTM-P10.2 Minimum Fourier Measurements for Stable Recovery of Block Sparse Signal
- SPTM-P10.3 Modified Adaptive Basis Pursuits for Recovery of Correlated Sparse Signals
- SPTM-P10.4 Band-Limited Extrapolation on the Sphere for Signal Reconstruction in the Presence of Noise
- SPTM-P10.5 combining Spread Spectrum Compressive sensing with Rakeness for low frequency modulation in RMPI architecture
- SPTM-P10.6 A Homotopy Recursive-in-Model-Order Algorithm for Weighted Lasso
- SPTM-P10.7 Fused Lasso with a Non-Convex Sparsity Inducing Penalty
- SPTM-P10.8 Practical ReProCS for Separating Sparse and Low-dimensional Signal Sequences from their Sum -- Part 1
- SPTM-P10.9 Compressed Sensing for Block-Sparse Smooth Signals
- SPTM-P10.10 Compressive Circulant Matrix Based Analog to Information Conversion
- SPTM-P10.11 Time-Varying Filtering and Separation of Nonstationary FM Signals in Strong Noise Environments
- SPTM-P10.12 The natural scale of signals: pulse duration and superoscillations
- SPTM-P10.13 System Approximation with General Measurement Functionals
- SPTM-P10.14 Active Target Detection with Mobile Agents
SPTM-P11: Estimation
Room: Poster Area 4
Chair: Alle-Jan van der Veen (TUDelft, The Netherlands)
- SPTM-P11.1 Robust Measure Transformed MUSIC for DOA Estimation
- SPTM-P11.2 Monte-Carlo estimation from observation on Stiefel manifold
- SPTM-P11.3 Quasi-maximum likelihood estimator of multiple polynomial-phase signals
- SPTM-P11.4 Distance Estimation Based on Phase Detection with Robust Chinese Remainder Theorem
- SPTM-P11.5 A Hybrid Data Association Model for Efficient Multi-Target Maximum Likelihood Estimation
- SPTM-P11.6 RSS-based Localization in Non-homogeneous Environments
- SPTM-P11.7 A New Importance-Sampling ML Estimator of Time Delays and Angles of Arrival in Multipath Environments
- SPTM-P11.8 Sparse Gaussian Noisy Independent Component Analysis
- SPTM-P11.9 Vector l0 Latent-Space Principal Component Analysis
- SPTM-P11.10 Sparse Component Analysis via dyadic Cyclic Descent
- SPTM-P11.11 Blind Separation of Dependent Sources With a Bounded Component Analysis Deflationary Algorithm
- SPTM-P11.12 On Blind Channel Identification and Equalization Over Galois Fields
- SPTM-P11.13 Robust Blind Calibration via Total Least Squares
- SPTM-P11.14 An Optimum Shrinkage Estimator Based on Minimum Probability of Error Criterion and Application to Signal Denoising
SPCOM-P6: Channel models, and source, channel and network coding
Room: Poster Area 5
Chair: Philippe Ciblat (Telecom ParisTech, France)
- SPCOM-P6.1 Analog Joint Source Channel Coding for Block Fading Multiple Access Channels
- SPCOM-P6.2 Optimization of zero-delay mappings for distributed coding by deterministic annealing
- SPCOM-P6.3 Analog Joint Source Channel Coding For Gaussian Broadcast Channels
- SPCOM-P6.4 Variable-Length Versus Fixed-Length Coding: On Tradeoffs for Soft-Decision Decoding
- SPCOM-P6.5 Asymptotic Analysis and Design of LDPC Codes for Laurent-based Optimal and Suboptimal CPM Receivers
- SPCOM-P6.6 Achieving Full-Diversity And Fast Maximum Likelihood Decoding In Asynchronous Analog Network Coding
- SPCOM-P6.7 A Study on the Statistical Modeling of Fading and its Effects on System Performance Using SIRP and SDP Methods
- SPCOM-P6.8 Geometry-Based Stochastic Modeling and Estimation of Vehicle to Vehicle Channels
- SPCOM-P6.9 A Grey-Box Modelling Approach for the Nonlinear Parametric Channel
- SPCOM-P6.10 Multi-scale Multi-lag Channel Estimation using Low rank Structure of Received Signal
IVMSP-P8: Image Feature Extraction
Room: Poster Area 6
Chair: Lina Karam (Arizona State University, USA)
- IVMSP-P8.1 Multi-image aggregation for better visual object retrieval
- IVMSP-P8.2 Investigating and Predicting Social and Visual Image Interestingness on Social Media by Crowdsourcing
- IVMSP-P8.3 Sparse Moving Factorization for Subspace Video Stabilization
- IVMSP-P8.4 A Scale-Adaptive Extension to Methods based on LBP using Scale-Normalized Laplacian of Gaussian Extrema in Scale-Space
- IVMSP-P8.5 Individualized Matching Based On Logo Density For Scalable Logo Recognition
- IVMSP-P8.6 Finger detection and Hand Posture Recognition Based on Depth Information
- IVMSP-P8.7 Change detection based on features invariant to monotonic transforms and spatial constrained matching
- IVMSP-P8.8 Change Detection on SAR Images Using Divisive Normalization-based Image Representation
- IVMSP-P8.9 Motion detection with spatiotemporal sequences
- IVMSP-P8.10 A Vanishing Point-Based Global Descriptor for Manhattan Scenes
- IVMSP-P8.11 People Counting With Image Retrieval Using Compressed Sensing
- IVMSP-P8.12 Intrinsic prior for Bayesian classification of texture images
- IVMSP-P8.13 Information bottleneck-based relevant knowledge representation in large-scale video surveillance systems
- IVMSP-P8.14 Functional Relevant Multichannel Kernel Adaptive Filter for Human Activity Analysis
BISP-P4: Signal detection in biomedical applications
Room: Poster Area 7
- BISP-P4.1 Physiological Parameter Monitoring of Drivers based on Video Data and Independent Vector Analysis
- BISP-P4.2 Non-Invasive Monitoring Of Fetal Movements Using Time-Frequency Features Of Accelerometry
- BISP-P4.3 Real-Time Swallowing Detection Based on Tracheal Acoustics
- BISP-P4.4 Fuzzy Logic Based Emotion Classification
- BISP-P4.5 Mobile real-time arousal detection
- BISP-P4.6 Design of a reliable processing pipeline for the non-intrusive measurement of feet trajectories with lasers
- BISP-P4.7 PhotoECG: Photoplethysmography to Estimate ECG Parameters
- BISP-P4.8 Power-Efficient Joint Compressed Sensing of Multi-Lead ECG Signals
- BISP-P4.9 A weighted l1 minimization algorithm for compressed sensing ECG
- BISP-P4.10 Robust classification between normal and abnormal lung sounds using adventitious-sound and heart-sound models
- BISP-P4.11 Compressive Sensing of ECG Signals Based on Mixed Pseudonorm of the First- and Second-Order Differences
- BISP-P4.12 Online Bayesian Apnea-Bradycardia Detection using Auto-Regressive Models
- BISP-P4.13 Learning-based Heart Rate Detection from Remote Photoplethysmography Features
- BISP-P4.14 Fetal Heart Rate Detection Using VPW-FRI
AASP-P6: Spatial Audio II, Signal Enhancement II
Room: Poster Area 8
Chair: Dorothea Kolossa (Ruhr-Universität Bochum, Germany)
- AASP-P6.1 Sparse Sound Field Representation in Recording and Reproduction for Reducing Spatial Aliasing Artifacts
- AASP-P6.2 Robust beamforming under uncertainties in the loudspeakers directivity pattern
- AASP-P6.3 The Design of Ambisonic Reproduction System based on Dynamic Gain Parameters
- AASP-P6.4 Fast Modelling of Pinna Spectral Notches from HRTFs using Linear Prediction Residual Cepstrum
- AASP-P6.5 Enhancing Vertical Localization with Image-guided Selection of Non-individual Head-Related Transfer Functions
- AASP-P6.6 HRTF Magnitude Synthesis via Sparse Representation of Anthropometric Features
- AASP-P6.7 Anthropometric-based customization of Head-Related Transfer Functions using Isomap in the horizontal plane
- AASP-P6.8 MMSE-Optimal Enhancement of Complex Speech Coefficients With Uncertain Prior Knowledge of the Clean Speech Phase
- AASP-P6.9 Speech Enhancement using Segmental Nonnegative Matrix Factorization
- AASP-P6.10 An Evaluation of Excitation Feature Prediction in A Hybrid Approach to Electrolaryngeal Speech Enhancement
- AASP-P6.11 ML Estimation of Memoryless Nonlinear Distortions in Audio Signals
MLSP-P3: Learning theory I
Room: Poster Area 9
Chair: Cédric Richard (Université de Nice Sophia-Antipolis, France)
- MLSP-P3.1 Network Inference and Change Point Detection for Piecewise-Stationary Time Series
- MLSP-P3.2 A Maximal Figure-of-Merit Learning Approach to Maximizing Mean Average Precision with Deep Neural Network Based Classifiers
- MLSP-P3.3 An Efficient Sparse Kernel Adaptive Filtering Algorithm Based on Isomorphism Between Functional Subspace and Euclidean Space
- MLSP-P3.4 Improved Convergence Performance of Adaptive Algorithms Through Logarithmic Cost
- MLSP-P3.5 Mixed Maps for Learning a Kolmogoroff-Nagumo-Type Average Element on the Compact Stiefel Manifold
- MLSP-P3.6 Estimators for Unnormalized Statistical Models Based On Self Density Ratio
- MLSP-P3.7 Clustering Based Online Learning in Recommender Systems: A Bandit Approach
- MLSP-P3.8 Looking for the Same Needle in Multiple Haystacks: Performance Bounds
- MLSP-P3.9 Projentropy: Using entropy to optimize spatial projections
- MLSP-P3.10 Improving The Tracking Ability of KRLS Using Kernel Subspace Pursuit
- MLSP-P3.11 Non-uniform Feature Sampling for Decision Tree Ensembles
- MLSP-P3.12 Extreme-Value Graphical models with Multiple Covariates
- MLSP-P3.13 Learning Multiple Concepts with Incremental Diverse Density
MMSP-P3: Multimedia and Multimodal Signal Processing II
Room: Poster Area 10
Chair: Stefano Tubaro (Politecnico di Milano, Italy)
- MMSP-P3.1 Audio Tampering Detection Using Multimodal Features
- MMSP-P3.2 Synthesizing Real-time Speech-Driven Facial Animation
- MMSP-P3.3 Speech driven talking head from estimated articulatory features
- MMSP-P3.4 Evaluation of HMM-based visual laughter synthesis
- MMSP-P3.5 Sentiment retrieval on web reviews using spontaneous natural speech
- MMSP-P3.6 Detecting Planar Surface Using a Light-Field Camera with Application to Distinguishing Real Scenes From Printed Photos
- MMSP-P3.7 Power-Spectral Analysis of Head Motion Signal for Behavioral Modeling in Human Interaction
- MMSP-P3.8 Late Fusion and Calibration for Multimedia Event Detection Using Few Examples
- MMSP-P3.9 Temporal Synchronization of Multiple Audio Signals
- MMSP-P3.10 Human Action Recognition using Associated Depth and Skeleton Information
- MMSP-P3.11 Exploring the use of ENF for multimedia synchronization
- MMSP-P3.12 Continuous Visual Speech Recognition for Multimodal Fusion
10:30 AM - 11:00 AM
Coffee break
11:00 AM - 1:00 PM
SLTC-L8: Speech Intelligibility Enhancement
Room: Cavaniglia
Chairs: Rainer Martin (Ruhr-University Bochum, Germany), Yannis Stylianou (University of Crete, Greece)
- 11:00 Deep Recurrent De-Noising Auto-Encoder and blind de-reverberation for reverberated speech recognition
- 11:20 Learning Spectral Mapping for Speech Dereverberation
- 11:40 Restoration of Instantaneous Amplitude and Phase using Kalman filter for Speech Enhancement
- 12:00 On the use of Early-to-Late Reverberation Ratio for ASR in reverberant environments
- 12:20 Comparison of post-processing methods for intelligibility enhancement of narrowband speech in a mobile phone framework
- 12:40 Simple and artefact-free spectral modifications for enhancing the intelligibility of casual speech
SPTM-L6: Performance Analysis and Bounds
Room: Basilica
Chairs: Kutluyıl Doğançay (University of South Australia, Australia), K. v. s. Hari (Indian Institute of Science, India)
- 11:00 Performance Bounds for Joint Estimation of Ionospheric and Target Parameters in MIMO-OTH Radar
- 11:20 Waveform Selection for Range and Doppler Estimation via Barankin Bound Signal-to-Noise Ratio Threshold
- 11:40 A Ziv-Zakai type bound for hybrid parameter estimation
- 12:00 Fundamental Localization Accuracy in Narrowband Array-based Systems
- 12:20 Ziv-Zakai Bound for Time Delay Estimation of Unknown Deterministic Signals
- 12:40 Approximate Least Squares
BISP-L2: EEG data processing I
Room: Polveriera
Chairs: Michael Liebling (University of California, Santa Barbara, USA), Ahmed Tewfik (University of Texas, Austin, USA)
- 11:00 Neural Decoding Using a Nonlinear Generative Model for Brain-Computer Interface
- 11:20 Subspace Denoising of EEG Artefacts Via Multivariate EMD
- 11:40 Bayesian detection of single-trial event-related potentials
- 12:00 Assessment of new spectral features for EEG-based emotion recognition
- 12:20 Synchrony Analysis of Paroxysmal Gamma Waves in Meditation EEG
- 12:40 Reduced-rank neural activity index for EEG/MEG multi-source localization
AASP-L4: Sound Field Analysis and Reproduction
Room: Scherma
Chairs: Jean-Marc Jot (DTS, Inc., USA), Boaz Rafaely (Ben-Gurion University of the Negev, Israel)
- 11:00 Room Statistics and Direct-to-reverberant Ratio Estimation from Dual-channel Signals
- 11:20 Non-intrusive estimation of the level of reverberation in speech
- 11:40 A Method for Converting Between Cylindrical and Spherical Harmonic Representations of Sound Fields
- 12:00 Multizone Soundfield Reproduction In Reverberant Rooms Using Compressed Sensing Techniques
- 12:20 Generation of multiple sound zones by spatial filtering in wavenumber domain using a linear array of loudspeakers
- 12:40 PDE-based Interpolation Method for Optically Visualized Sound Field
SPCOM-L4: Energy harvesting and management
Room: Teatrino
Chairs: Rahul Vaze (TIFR Mumbai, India), Rui Zhang (National University of Singapore, Singapore)
- 11:00 Energy Consumption in multi-user MIMO systems: Impact of user mobility
- 11:20 Robust Transmit Designs for an Energy Harvesting Multicast System
- 11:40 Joint Transceiver design for MISO SWIPT interference channel
- 12:00 Energy-constrained Throughput Maximization for Point-to-Point Communications
- 12:20 Energy Harvesting for Relay-Assisted Communications
- 12:40 Interference Power Recycling in Two-Scale Ad Hoc Wireless Networks
SS8: Social Nets: Learning and Optimization
Room: Volta
Chairs: Georgios B. Giannakis (University of Minnesota, USA), Gonzalo Mateos (University of Minnesota, USA)
- 11:00 State-Dependent Opinion Dynamics
- 11:20 A Proximal Gradient Algorithm for Tracking Cascades Over Networks
- 11:40 Information aggregation in a beauty contest game
- 12:00 Online ratings: convergence towards a positive perspective?
- 12:20 Towards a Spectral Characterization of Signals Supported on Small-World Networks
- 12:40 Unsupervised Social Media Events Clustering using User-centric Parallel SPLIT-N-MERGE Algorithms
SLTC-P13: Paralinguistic Speech Recognition
Room: Poster Area 1
Chair: Nick Campbell (Trinity College Dublin, Canada)
- SLTC-P13.1 Emotions Are A Personal Thing: Towards Speaker-Adaptive Emotion Recognition
- SLTC-P13.2 A Feature Selection and Feature Fusion Combination Method for Speaker-Independent Speech Emotion Recognition
- SLTC-P13.3 Automatic detection of expressed emotion in Parkinson's disease
- SLTC-P13.4 Introducing Shared-Hidden-Layer Autoencoders for Transfer Learning and their Application in Acoustic Emotion Recognition
- SLTC-P13.5 Social Signal Classification Using Deep BLSTM Recurrent Neural Networks
- SLTC-P13.6 Visual-Only Discrimination between Native and Non-Native Speech
- SLTC-P13.7 Simplified and Supervised i-vector Modeling for Speaker Age Regression
- SLTC-P13.8 Affective language model adaptation via corpus selection
- SLTC-P13.9 Inferring social relationships in a phone call from a single party's speech
- SLTC-P13.10 Automatic Characterization of Speaking Styles in Educational Videos
- SLTC-P13.11 Automatic Analysis of Speech Quality for Aphasia Treatment
- SLTC-P13.12 Ecologically Valid Long-term Mood Monitoring of Individuals with Bipolar Disorder Using Speech
- SLTC-P13.13 Automatic Detection of Psychological Distress Indicators and Severity Assessment in Crisis Hotline Conversations
- SLTC-P13.14 Mandarin tone classification without pitch tracking
SLTC-P14: Language Models
Room: Poster Area 2
Chair: Shinji Watanabe (Mitsubishi Electric Research Laboratories, USA)
- SLTC-P14.1 Role Play Dialogue Topic Model for Language Model Adaptation in Multi-Party Conversation Speech Recognition
- SLTC-P14.2 Static interpolation of exponential n-gram models using features of features
- SLTC-P14.3 Improving Language Modeling by Using Distance and Co-Occurrence Information of Word-Pairs and its Application to LVCSR
- SLTC-P14.4 Optimization of Neural Network Language Models for Keyword Search
- SLTC-P14.5 Paraphrastic Neural Network Language Models
- SLTC-P14.6 Variance Regularization of RNNLM for Speech Recognition
- SLTC-P14.7 Query-based Composition for Large-scale Language Model in LVCSR
- SLTC-P14.8 Efficient Lattice Rescoring Using Recurrent Neural Network Language Models
- SLTC-P14.9 Code Switch Language Modeling With Functional Head Constraint
- SLTC-P14.10 A Bin-Based Ontological Framework for Low-Resource N-Gram Smoothing in Language Modelling
SPTM-P12: Signal Sampling, Sensing and Reconstruction II
Room: Poster Area 3
Chair: Isao Yamada (Tokyo Institute of Technology, Japan)
- SPTM-P12.1 Frames from Generalized Group Fourier Transforms and SL(2, q)
- SPTM-P12.2 Block Processing with Iterative Correction Filters for Time-Interleaved ADCs
- SPTM-P12.3 Ramanujan-sum expansions for finite duration (FIR) sequences
- SPTM-P12.4 Second-Order Total Generalized Variation Constraint
- SPTM-P12.5 Magnitude-constrained sequence design with application in MRI
- SPTM-P12.6 Sparsity Fine Tuning in Wavelet Domain with Application to Compressive Image Reconstruction
- SPTM-P12.7 Sparse Signal Recovery under Poisson Statistics for Online Marketing Applications
- SPTM-P12.8 Iterative Soft-Thresholding for Time-Varying Signal Recovery
- SPTM-P12.9 Algebraic Phase Unwrapping over Collection of Triangles Based on Two-dimensional Spline Smoothing
- SPTM-P12.10 Information-Maximizing Prefilters for Quantization
- SPTM-P12.11 Matrix Recovery From Quantized and Corrupted Measurements
- SPTM-P12.12 Selective analytic signal construction from a non-uniformly sampled bandpass signal
- SPTM-P12.13 Denoising using multi-stage randomized Orthogonal Matching Pursuit
DISPS-P1: Design Methods and Optimization for DSP
Room: Poster Area 4
Chair: Marco Mattavelli (EPFL, Switzerland)
- DISPS-P1.1 Efficient Software Synthesis of Dynamic Dataflow Programs
- DISPS-P1.2 Cooperative CPU+GPU Deblocking Filter Parallelization for High Performance HEVC Video Codecs
- DISPS-P1.3 Efficient duty-cycle mismatch compensation in digital transmitter
- DISPS-P1.4 A Methodology for Optimizing Buffer Sizes of Dynamic Dataflow FPGAs Implementations
- DISPS-P1.5 Design of Sparse-Signal Processing in Radar Systems
- DISPS-P1.6 3-D Stacked Memory System Architecture Exploration by ESL Virtual Platform and Reconfigurable Stacking Memory Architecture in 3D-DSP SoC System
- DISPS-P1.7 Computing Resource Minimization with Content-aware Workload Estimation in Cloud-based Surveillance Systems
- DISPS-P1.8 Low Complexity Subband Analysis using Quadrature Mirror Filters
- DISPS-P1.9 Leakage-Aware Scratch-Pad Memory Banking for Embedded Multidimensional Signal Processing
- DISPS-P1.10 Fault Tolerance Analysis of Digital Feed-Forward Deep Neural Networks
- DISPS-P1.11 Embedding Polynomial Time Memory Mapping and Routing Algorithms on-chip to Design Configurable Decoder Architectures
- DISPS-P1.12 Robust Decision Feedback Equalizer Scheme by Using Sphere-Decoding Detector
SPCOM-P7: Sensing and learning networks
Room: Poster Area 5
Chair: Milica Stojanovic (Northeastern University, USA)
- SPCOM-P7.1 Single Bit and Reduced Dimension Diffusion Strategies Over Distributed Networks
- SPCOM-P7.2 Sigma Point Belief Propagation
- SPCOM-P7.3 On the Stochastic Modeling of Desynchronization Convergence in Wireless Sensor Networks
- SPCOM-P7.4 Distributed Bayesian estimation of arrival rates in asynchronous monitoring networks
- SPCOM-P7.5 Distributed detection with censoring sensors under dependent observations
- SPCOM-P7.6 Energy-saving gossip algorithm for compressed sensing in multi-agent systems
- SPCOM-P7.7 Distributed blind system identification in sensor networks
- SPCOM-P7.8 Decentralized vs. Centralized Scheduling in Wireless Sensor Networks For Data Fusion
- SPCOM-P7.9 Probabilistic sensor management for target tracking via compressive sensing
- SPCOM-P7.10 Sparsity-Promoting Adaptive Sensor Selection for Non-Linear Filtering
- SPCOM-P7.11 Topology Optimization for Energy-efficient Communications in Consensus Wireless Networks
IVMSP-P9: Image Segmentation
Room: Poster Area 6
Chair: Mark Liao (Academia Sinica, Taiwan)
- IVMSP-P9.1 First Maurdor 2013 Evaluation Campaign in Scanned Document Image Processing
- IVMSP-P9.2 GPU-accelerated joint 1D and 2D barcode localization on smartphones
- IVMSP-P9.3 Joint Learning of Foreground Region Labeling and Depth Ordering
- IVMSP-P9.4 Multi-Scale Crest Line Extration based on Half Gaussian Kernels
- IVMSP-P9.5 Hierarchical Image Content Analysis with an Embedded Marked Point Process Framework
- IVMSP-P9.6 Combination of Graph Theoretic Grouping and Time-Frequency Analysis for Image Segmentation
- IVMSP-P9.7 Automatic initialization for naval application of graph segmentation techniques: a comparative study
BISP-P5: Processing and applications in Ultrasound
Room: Poster Area 7
Chair: François Varray (CREATIS, Université de Lyon, France)
- BISP-P5.1 A new method for 2D-vector blood flow imaging based on unconventional beamforming techniques
- BISP-P5.2 Dynamic Receive Aperture Downsampling for Ultrasound Imaging
- BISP-P5.3 Segmentation of Ultrasound Images for Phlebotomy Applications
- BISP-P5.4 A Nonlinear Ultrasound Propagation Simulator using the Slowly Varying Envelope Approximation
- BISP-P5.5 An Integrated System For The Evaluation of Flow Mediated Dilation
- BISP-P5.6 Amplitude and Phase Estimator for Real-Time Biomedical Spectral Doppler Applications
- BISP-P5.7 High Frame Rate Compounding for Nonlinear B/A Parameter Ultrasound Imaging in Echo Mode - Simulation Results
- BISP-P5.8 Real-time Implementation of a Novel Algorithm For Ultrasound Freehand Elastography of Breast Lesions
AASP-P7: Reverberation Reduction, Music Information Retrieval II
Room: Poster Area 8
Chair: Sharon Gannot (Bar-Ilan University, Israel)
- AASP-P7.1 Adaptive Multichannel Equalization Applied To Room Acoustics Exploiting the Sparsity of Target Response
- AASP-P7.2 Probabilistic Integration of Diffuse Noise Suppression and Dereverberation
- AASP-P7.3 Speech dereverberation using weighted prediction error with Laplacian model of the desired signal
- AASP-P7.4 Frequency-Domain Single-Channel Inverse Filtering for Speech Dereverberation: Theory and Practice
- AASP-P7.5 Single channel reverberation suppression based on sparse linear prediction
- AASP-P7.6 Blind RT60 estimation robust across room sizes and source distances
- AASP-P7.7 Towards Efficient Audio Thumbnailing
- AASP-P7.8 Learning to segment songs with ordinal linear discriminant analysis
- AASP-P7.9 Vocal Timbre Analysis Using Latent Dirichlet Allocation and Cross-Gender Vocal Timbre Similarity
- AASP-P7.10 Modified LASSO Screening for Audio Word-based Music Classification Using Large-scale Dictionary
- AASP-P7.11 Audio Part Mixture Alignment Based on Hierarchical Nonparametric Bayesian Model of Musical Audio Sequence Collection
- AASP-P7.12 A Supervised Approach to Hierarchical Metrical Cycle Tracking from Audio Music Recordings
- AASP-P7.13 Improving Instrument Recognition in Polyphonic Music Through System Integration
MLSP-P4: Sparsity
Room: Poster Area 9
Chair: Volkan Cevher (Ecole Polytechnique Federale de Lausanne, Switzerland)
- MLSP-P4.1 Collaborative Representation, Sparsity or Nonlinearity: What Is Key to Dictionary Based Classification?
- MLSP-P4.2 Learning high-dimensional nonlinear mapping via compressed sensing
- MLSP-P4.3 Scalable Sparse Approximation of a Sample Mean
- MLSP-P4.4 A Fast Variational Approach for Bayesian Compressive Sensing with Informative Priors
- MLSP-P4.5 Dictionary Learning for Sparse Representation: Complexity and Algorithms
- MLSP-P4.6 Change Detection in Streams of Signals with Sparse Representations
- MLSP-P4.7 Sparse kernel recursive least squares using l1 regularization and a fixed-point sub-iteration
- MLSP-P4.8 Doubly Sparse Transform Learning With Convergence Guarantees
- MLSP-P4.9 An Improved Auto-Calibration Algorithm Based on Sparse Bayesian Learning Framework
- MLSP-P4.10 Dictionary Training for Sparse Representation as Generalization of K-means Clustering
- MLSP-P4.11 Blockwise Coordinate Descent Schemes for Sparse Representation
SAM-P4: MIMO Radar
Room: Poster Area 10
Chair: Athina Petropulu (Rutgers, The State University of New Jersey, USA)
- SAM-P4.1 Closed Form Fourier-Based Transmit Beamforming for MIMO Radar
- SAM-P4.2 MIMO Radar Capability on Powerful Jammers Suppression
- SAM-P4.3 Unimodular Code Design for MIMO Radar Using Bhattacharyya Distance
- SAM-P4.4 MIMO Radar Performance Analysis under K-distributed Clutter
- SAM-P4.5 MIMO Radar Demystified and Where it Makes Sense to Use
- SAM-P4.6 MIMO Radar Filterbank Design for Interference Mitigation
- SAM-P4.7 Generalized Ambiguity Function for the MIMO Radar With Correlated Waveforms
- SAM-P4.8 Signal Model and Detection Performance for MIMO-OTH Radar with Multipath Ionospheric Propagation and Non-Point Target
- SAM-P4.9 Minimum sidelobe beampattern design for MIMO radar systems: A Robust Approach
- SAM-P4.10 Approaching Peak Correlation Bounds Via Alternating Projections
- SAM-P4.11 The Significant Gains from Optimally Processed Multiple Signals of Opportunity and Multiple Receive Stations in Passive Radar
1:00 PM - 2:30 PM
Lunch Time
2:30 PM - 2:45 PM
Shaping the future: the innovative dimension of Research & Technology
Vice Admiral Osvaldo Brogi (Marina Militare Italiana (MMI))
2:45 PM - 3:45 PM
PT3: Plenary Talk: Green radar state of art: theory, practice and way ahead (Room Cavaniglia)
Keynote speaker: Alfonso Farina (Selex ES, Italy)
3:45 PM - 4:15 PM
Coffee break
4:15 PM - 6:15 PM
SLTC-L9: Language Identification
Room: Cavaniglia
Chairs: Najim Dehak (Massachusetts Institute of Technology, USA), Haizhou Li (Institute for Infocomm Research, Singapore)
- 4:15 Improved Phonotactic Language Recognition Based on RNN Feature Reconstruction
- 4:35 Language Recognition System Using Language Branch Discriminative Information
- 4:55 Introducing Attribute Features to Foreign Accent Recognition
- 5:15 Automatic Language Identification using Deep Neural Networks
- 5:35 Extended Phone Log-Likelihood Ratio Features and Acoustic-based I-Vectors for Language Recognition
- 5:55 Subspace Gaussian Mixture Model for Computer-Assisted Language Learning
IVMSP-L4: Image Analysis II
Room: Basilica
Chair: Alessandro Foi (Tampere University of Technology, Finland)
- 4:15 Regularizing inverse problems in image processing with a manifold-based model of overlapping patches
- 4:35 Gaussian-Cauchy mixture modeling for robust signal-dependent noise estimation
- 4:55 New Bivariate Statistical Model of Natural Image Correlations
- 5:15 A multivariate statistical model for multiple images acquired by homogeneous or heterogeneous sensors
- 5:35 Saliency Driven Clustering for Salient Object Detection
- 5:55 2D Hilbert-Huang Transform
SS9: Array signal processing for radio astronomy: the SKA is the future
Room: Polveriera
Chairs: Stefan J. Wijnholds (ASTRON, The Netherlands), Alfonso Farina (SELEX-SI, Italy)
- 4:15 Signal Processing Challenges for Radio Astronomical Arrays
- 4:35 RFI Spatial Processing at Nançay Observatory: Approaches and Experiments
- 4:55 Robust Radio Interferometric Calibration
- 5:15 Holistic Power Analysis of Implementation Alternatives for a Very Large Scale Synthesis Array with Phased Array Stations
- 5:35 A Computationally Efficient Self-Calibration Algorithm for the LOFAR Radio Astronomical Array
- 5:55 PURIFY: a new algorithmic framework for next-generation radio-interferometric imaging
MLSP-L2: Neural Network Methods
Room: Scherma
Chairs: Li Deng (Microsoft Research, USA), Konstantinos Diamantaras (TEI of Thessaloniki, Greece)
- 4:15 On-Line Continuous-Time Music Mood Regression with Deep Recurrent Neural Networks
- 4:35 Phone sequence modeling with recurrent neural networks
- 4:55 Deep Learning of Split Temporal Context for Automatic Speech Recognition
- 5:15 Minimum Variance Extreme Learning Machine for Human Action Recognition
- 5:35 3D gesture classification with convolutional neural networks
- 5:55 Deep Hybrid Networks with good out-of-sample object recognition
SPCOM-L5: Consensus and distributed estimation
Room: Teatrino
Chair: Amir Leshem (Bar-Ilan University, Israel)
- 4:15 On The Convergence of Average Consensus With Generalized Metropolis-Hasting Weights
- 4:35 Decentralized Linearized Alternating Direction Method of Multipliers
- 4:55 Optimal Power Allocation for Distributed BLUE Estimation with Linear Spatial Collaboration
- 5:15 Robust Detection and Social Learning in Tandem Networks
- 5:35 Consensus algorithms with state-dependent weights
- 5:55 Incentivizing Information Sharing in Networks
SPTM-L7: Advances in Adaptive Filtering
Room: Volta
Chairs: Kostas Berberidis (University of Patras, Greece), Sergios Theodoridis (University of Athens, Greece)
- 4:15 Distributed Least Mean Squares Strategies for Sparsity-Aware Estimation over Gaussian Markov Random Fields
- 4:35 Shrinkage Tuning Based on An Unbiased MSE Estimate for Sparsity-aware Adaptive Filtering
- 4:55 Distributed Bayesian learning with a Bernoulli model
- 5:15 Diffusion LMS for clustered multitask networks
- 5:35 An Adaptive Line Enhancer Based On The Convex Combination of Two IIR Filters
- 5:55 An Adaptive Projected Subgradient based Algorithm for Robust Subspace Tracking
SLTC-P15: Robust Speech Recognition II
Room: Poster Area 1
Chair: Geoffery Zweig (Microsoft Research, USA)
- SLTC-P15.1 Noise-robust Speech Recognition with Exemplar-based Sparse Representations Using Alpha-Beta Divergence
- SLTC-P15.2 Extension of uncertainty propagation to dynamic MFCCs for noise robust ASR
- SLTC-P15.3 Fusion of multiple uncertainty estimators and propagators for noise robust ASR
- SLTC-P15.4 A Compact Formulation of Turbo Audio-Visual Speech Recognition
- SLTC-P15.5 Estimating Room Acoustic Parameters for Speech Recognizer Adaptation and Combination in Reverberant Environments
- SLTC-P15.6 Noise-Adaptive LDA: A New Approach for Speech Recognition Under Observation Uncertainty
- SLTC-P15.7 Impact of single-microphone dereverberation on DNN-based meeting transcription systems
- SLTC-P15.8 Recurrent Deep Neural Networks for Robust Speech Recognition
- SLTC-P15.9 Factorized adaptation for deep neural network
- SLTC-P15.10 Using neural network front-ends on far field multiple microphones based speech recognition
- SLTC-P15.11 Robust far-field spoken command recognition for home automation combining adaptation and multichannel processing
- SLTC-P15.12 Highly Accurate Phonetic Segmentation Using Boundary Correction Models and System Fusion
- SLTC-P15.13 Fusion of Diverse denoising systems for Robust Automatic Speech Recognition
- SLTC-P15.14 Unsupervised non-parametric Bayesian modeling of non-stationary noise for model-based noise suppression
SLTC-P16: Deep Neural Networks in Speech Recognition II
Room: Poster Area 2
Chair: Patrick Nguyen (Big Data Startup, USA)
- SLTC-P16.1 A Comparison of Two Optimization Techniques for Sequence Discriminative Training of Deep Neural Networks
- SLTC-P16.2 Joint Training of convolutional and non-convolutional Neural Networks
- SLTC-P16.3 Reduction of Acoustic Model Training Time and Required Data Passes via Stochastic Approaches to Maximum Likelihood and Discriminative Training
- SLTC-P16.4 Data Augmentation for Deep Neural Network Acoustic Modeling
- SLTC-P16.5 Asynchronous Stochastic Optimization for Sequence Training of Deep Neural Networks
- SLTC-P16.6 Joint Acoustic Modeling of Triphones and Trigraphemes by Multi-Task Learning Deep Neural Networks for Low-Resource Speech Recognition
- SLTC-P16.7 Standalone Training of Context-Dependent Deep Neural Network Acoustic Models
- SLTC-P16.8 GMM-free DNN training
- SLTC-P16.9 Multilingual Shifting Deep Bottleneck Features for low-resource ASR
- SLTC-P16.10 A Family of Discriminative Training Criteria based on the f-Divergence for Deep Neural Networks
- SLTC-P16.11 Lattice based optimization of bottleneck feature extractor with linear transformation
- SLTC-P16.12 BUT Neural Network features for spontaneous Vietnamese in BABEL
- SLTC-P16.13 Sequence Training of Multiple Deep Neural Networks for Better Performance and Faster Training Speed
- SLTC-P16.14 Single-channel Mixed Speech Recognition Using Deep Neural Networks
SPTM-P13: Estimation and Optimization
Room: Poster Area 3
Chair: Jean-Yves Tourneret (University of Toulouse & IRIT/ENSEEIHT/TéSA, France)
- SPTM-P13.1 A Fast Eigen Solution for Homogeneous Quadratic Minimization with at most three Constraints
- SPTM-P13.2 Joint Frequency and Phasor Estimation under the KCL Constraint
- SPTM-P13.3 Robust Regularized Least Squares Estimation In the Presence of Bounded Data Uncertainties
- SPTM-P13.4 Convex separable problems with linear and box constraints
- SPTM-P13.5 Covariance Estimation in Elliptical Models with Convex Structure
- SPTM-P13.6 Optimal Stochastic Design For Multi-Parameter Estimation Problems
- SPTM-P13.7 Computing the Cramer-Rao bound of Markov random field parameters: Application to the Ising and the Potts models
- SPTM-P13.8 MERIT: A Monotonically Error-Bound Improving Technique for Unimodular Quadratic Programming
- SPTM-P13.9 Efficient Peak Extraction of Proton NMR Spectroscopy Using Lineshape Adaptation
- SPTM-P13.10 On Symmetric Alpha-Stable Noise After Short-Time Fourier Transformation
- SPTM-P13.11 On the Randomized Kaczmarz Algorithm
- SPTM-P13.12 Rényi information transfer: Partial Rényi transfer entropy and partial Rényi mutual information
- SPTM-P13.13 Approximate Least Squares Parameter Estimation with Structured Observations
- SPTM-P13.14 Maximum A Posteriori Estimation of Signal Rank
SPCOM-P8: Physical Layer Security
Room: Poster Area 4
Chair: Wing-Kin Ma (The Chinese University of Hong Kong, Hong Kong)
- SPCOM-P8.1 Hybrid-ARQ as a communications security measure
- SPCOM-P8.2 Secrecy Rate Maximization for MIMO Gaussian Wiretap Channels with Multiple Eavesdroppers via Alternating Matrix POTDC
- SPCOM-P8.3 Network-Coded Cooperation for a Two-User Wiretap Channel
- SPCOM-P8.4 Power Allocation for Energy-Constrained Cognitive Radios in the Presence of an Eavesdropper
- SPCOM-P8.5 Efficient jamming strategies on a MIMO Gaussian channel with known target signal covariance
- SPCOM-P8.6 The impact of finite-alphabet input on the secrecy-achievable rates for broadcast channel with confidential message
- SPCOM-P8.7 Destination Assisted Secret Wireless Communication with Cooperative Helpers
- SPCOM-P8.8 Artificial Noise Generated in MIMO Scenario: Optimal Power Design
- SPCOM-P8.9 Robust Relay Beamforming For Multiple-Antenna Amplify-And-Forward Relay System In The Presence Of Eavesdropper
SPCOM-P9: Synchronization, training and receiver design
Room: Poster Area 5
Chair: Eleftherios Kofidis (University of Piraeus, Greece)
- SPCOM-P9.1 Algorithmic Solutions for Pilot Design Optimization in Arbitrarily Correlated Scenarios
- SPCOM-P9.2 Training signal design for MIMO channel estimation with correlated disturbance
- SPCOM-P9.3 Inter-User Interference in Molecular Communication Networks
- SPCOM-P9.4 A Phase Likelihood-based Algorithm for Blind Identification of PSK signals
- SPCOM-P9.5 On the Accuracy of the High SNR Approximation of the Differential Entropy of Signals in Additive Gaussian Noise
- SPCOM-P9.6 Feedback Blind Phase Synchronization For QAM Signals Based On Circular Harmonic Decomposition
- SPCOM-P9.7 Distributed Clock Synchronization and Ranging in Time-Variant Wireless Networks
- SPCOM-P9.8 Joint MAP Time and Frequency Synchronization in Presence of Imperfect Channel State Information
- SPCOM-P9.9 Timestamp-Free Network Synchronization with Random Pairwise Message Exchanges
- SPCOM-P9.10 Single-Carrier Modulation with ML Equalization for Large-Scale Antenna Systems over Rician Fading Channels
- SPCOM-P9.11 Distributional Upper Bound on the Interference in Spatial Wireless Multiuser Ultrawideband Communication Systems
- SPCOM-P9.12 Frequency-Domain GLR Detection of Cyclostationary Signals in Frequency-Selective Channels
- SPCOM-P9.13 Joint CFO and I/Q imbalance compensation for the SC-IFDMA system uplink
- SPCOM-P9.14 Filter Bank Selection Diversity and Linear Equalization Over Frequency Selective Channels for Sinagle Carrier Transmission
IVMSP-P10: Interpolation and Super-resolution
Room: Poster Area 6
Chair: Oscar C. Au (HKUST, Hong Kong)
- IVMSP-P10.1 Joint Denoising and Demosaicking of Noisy CFA Images Based on Inter-color Correlation
- IVMSP-P10.2 Reconstruction of Multiview Images Taken with Non-Regular Sampling Sensors
- IVMSP-P10.3 Image Super-Resolution Via Kernel Regression of Sparse Coefficients
- IVMSP-P10.4 Image Super-Resolution Using Multi-layer Support Vector Regression
- IVMSP-P10.5 Single Color Image Super-resolution using Quaternion-based Sparse Representation
- IVMSP-P10.6 Block-Adaptive DCT-Wiener Image Up-Sampling
- IVMSP-P10.7 Image Retargeting with Protection of Object Arrangement
- IVMSP-P10.8 Fast and efficient Intra-frame deinterlacing using observation based bilateral filter
- IVMSP-P10.9 Ellipse fitting using finite rate of innovation principles
- IVMSP-P10.10 On the statistics of natural stochastic textures and their application in image processing
- IVMSP-P10.11 Analysis of Sampling Pattern and Luma-chroma Filter Design for Subpixel-based Image Downsampling
BISP-P6: EEG data processing II
Room: Poster Area 7
Chair: Liam Marnane (University College, Cork, Ireland)
- BISP-P6.1 On Application of Rational Discrete Short Time Fourier Transform in Epileptic Seizure Classification
- BISP-P6.2 EEG 'Diarization' for the Description of Neonatal Brain Injuries
- BISP-P6.3 Distributed eye blink artifact removal in a wireless EEG sensor network
- BISP-P6.4 Classification Of Kinetics Of Movement For Lower Limb Using Covariate Shift Method For Brain Computer Interface
- BISP-P6.5 Gradient Artifact Removal in Concurrently Acquired EEG Data using Independent Vector Analysis
- BISP-P6.6 Artifact reduction in multichannel pervasive EEG using hybrid WPT-ICA and WPT-EMD signal decomposition techniques
- BISP-P6.7 A performance study of various brain source imaging approaches
- BISP-P6.8 Novel Image Classification Based on Decision-Level Fusion of EEG and Visual Features
- BISP-P6.9 Modulation Frequency Analysis of Seizures in Neonatal EEG
- BISP-P6.10 Assessing Subjective Perception of Audio Quality by Measuring the Information Flow on the Brain-Response Channel
- BISP-P6.11 On the use of time-frequency features for detecting and classifying epileptic seizure activities in non-stationary EEG signals
- BISP-P6.12 Grading Brain Injury In Neonatal EEG Using SVM and Supervector Kernel
- BISP-P6.13 Beyond 2D for Brain-Computer Interfaces: Two 3D Extensions of the P300-Speller
- BISP-P6.14 Long-term movement tracking from Local Field Potentials with an adaptive open-loop decoder
AASP-P8: Echo Control II, Acoustic Event Analysis
Room: Poster Area 8
Chair: Emanuël Habets (International Audio Laboratories Erlangen, Germany)
- AASP-P8.1 Frequency Domain Acoustic Echo Reduction based on Kalman Smoother with Time-Varying Noise Covariance Matrix
- AASP-P8.2 Signal-based late residual echo spectral variance estimation
- AASP-P8.3 Look-Ahead Near-End Compensation in Acoustic Echo Cancellation
- AASP-P8.4 Frequency Domain Acoustic Echo Canceller That Handles Asynchronous A/D and D/A Clocks
- AASP-P8.5 Misalignment Analysis and Insights Into the Performance of Clipped-input LMS with Correlated Gaussian Data
- AASP-P8.6 Significance-Aware Hammerstein Group Models for Nonlinear Acoustic Echo Cancellation
- AASP-P8.7 Unsupervised Feature Extraction for Multimedia Event Detection and Ranking Using Audio Content
- AASP-P8.8 Robust Acoustic Feature Extraction for Sound Classification based on Noise Reduction
- AASP-P8.9 Generalized Gaussian Distribution Kullback-Leibler Kernel for Robust Sound Event Recognition
- AASP-P8.10 A Dual-Microphone Subband-based Voice Activity Detector Using Higher-Order Cumulants
- AASP-P8.11 Auditory-inspired pitch extraction using a synchrony capture filterbank and phase alignment
- AASP-P8.12 Fundamental Frequency and Model Order Estimation Using Spatial Filtering
- AASP-P8.13 Detecting pathological speech using contour modeling of harmonic-to-noise ratio
- AASP-P8.14 A Kalman Filter with Individual Control Factors for Echo Cancellation
MLSP-P5: Applications of MLSP
Room: Poster Area 9
Chair: Z. Jane Wang (University of British Columbia, Canada)
- MLSP-P5.1 Supervised Multi-Modal Topic Model for Image Annotation
- MLSP-P5.2 Compressed Prediction of Large-Scale Urban Traffic
- MLSP-P5.3 Scalable Fused Lasso SVM for Connectome-based Disease Prediction
- MLSP-P5.4 Spike train kernels for multiple neuron recordings
- MLSP-P5.5 Ensemble Random Projection for Multi-label Classification with Application to Protein Subcellular Localization
- MLSP-P5.6 Finding EEG space-time-scale localized features using matrix-based penalized discriminant analysis
- MLSP-P5.7 Questionnaire Simplification for Fast Risk Analysis of Children's Mental Health
- MLSP-P5.8 An eigen-based approach for complex-valued forecasting
- MLSP-P5.9 Semi-supervised dimensionality reduction on data with multiple representations for label propagation on facial images
- MLSP-P5.10 Online Semidefinite Programming for Power System State Estimation
- MLSP-P5.11 Cost-Effective Kernel Ridge Regression Implementation for Keystroke-Based Active Authentication System
- MLSP-P5.12 An Inference Framework for Detection of Home Appliance Activation from Voltage Measurements
- MLSP-P5.13 A new approach for classification of dolphin whistles
SAM-P5: Beamforming and Sensor Array Processing
Room: Poster Area 10
Chair: Xavier Mestre (CTTC, Spain)
- SAM-P5.1 Robust Adaptive Beamforming Based on Response Vector Optimization
- SAM-P5.2 MIMO RF Probe For Wide-area Indoor Human Motion Monitoring
- SAM-P5.3 Optimization of transmit signals to interfere eavesdropping in a wireless LAN
- SAM-P5.4 Optimal power Allocation and network beamforming for OFDM-based relay networks
- SAM-P5.5 A Conic Quadratic Programming Approach to Physical Layer Multicasting for Large-Scale Antenna Arrays
- SAM-P5.6 A Generalized Theorem on the Average Array Directivity Factor
- SAM-P5.7 Time-Varying STAP for Nonstationary Hot Clutter Cancellation
- SAM-P5.8 Knowledge-Aided Parametric Adaptive Matched Filter with Automatic Combining for Covariance Estimation
- SAM-P5.9 ISAR Imaging by Exploiting the Continuity of Target Scene
- SAM-P5.10 A network of HF surface wave radars for maritime surveillance: preliminary results in the German Bight
Friday, May 9
8:30 AM - 10:30 AM
SLTC-L10: Speech Enhancement
Room: Cavaniglia
Chairs: Tim Fingscheidt (Technische Universität Braunschweig, Germany), Frank Soong (Microsoft Research Asia, USA)
- 8:30 On Speech Quality Assessment of Artificial Bandwidth Extension
- 8:50 A Maximum A Posterior-based Reconstruction Approach to Speech Bandwidth Expansion in Noise
- 9:10 Exploiting The Baseband Phase Structure Of The Voiced Speech For Speech Enhancement
- 9:30 Non-linear Soft-sounds Enhancement for near-end Speech Intelligibility Improvement
- 9:50 Binaural Noise Suppression Based on an Unbiased Estimator of Target PSD in Complex Noise Environments
- 10:10 A Structure-Preserving Training Target For Supervised Speech Separation
SPTM-L8: Signal Processing on Networks
Room: Basilica
Chairs: Sergio Barbarossa (University of Rome La Sapienza", Italy), Franz Hlawatsch (Vienna University of Technology, Austria)
- 8:30 Large Deviations Analysis of Adaptive Distributed Detection
- 8:50 Distributed Decorrelation in Sensor Networks with Application to Distributed Particle Filtering
- 9:10 Ordinal Potential Functions for Network Selection in Heterogeneous Wireless Networks
- 9:30 Crawford-Sobel meet Lloyd-Max on the grid
- 9:50 Probabilistic ranking of multi-attribute items using indifference curve
- 10:10 Multi-Agent Distributed Large-Scale Optimization by Inexact Consensus Alternating Direction Method of Multipliers
SS10: Dynamic Geometry Compression
Room: Polveriera
Chair: Dinei Florencio (Microsoft Research, USA)
- 8:30 Hybrid compression of dynamic 3D mesh data
- 8:50 On Human Time-Varying Mesh Compression Exploiting Activity-Related Characteristics
- 9:10 Compression of Human Body Sequences Using Graph Wavelet Filter Banks
- 9:30 3D Geometry Representation using Multiview Coding of Image Tiles
- 9:50 Low Complexity Connectivity Driven Dynamic Geometry Compression for 3D Tele-Immersion
SS11: Signal Processing Techniques for Interference Alignment
Room: Scherma
Chair: Tharmalingam Ratnarajah (The University of Edinburgh, United Kingdom)
- 8:30 Link Adaptation for Interference Alignment with Imperfect CSIT
- 8:50 Ergodic Interference Alignment for the SIMO/MIMO Interference Channel
- 9:10 Interference Alignment (IA) and Coordinated Multi-Point (CoMP) with IEEE802.11ac feedback compression: testbed results
- 9:30 Performance Analysis of Distributed Cooperation under Uncoordinated Network Interference
- 9:50 Pilot-assisted ergodic interference alignment for wireless networks
- 10:10 Homotopy Continuation for Vector Space Interference Alignment in MIMO X Networks
MLSP-L3: Source Separation
Room: Teatrino
Chairs: Tulay Adali (University of Maryland Baltimore County, USA), Andrzej S Cichocki (RIKEN BSI, Laboratory for Advanced Brain Signal Processing, Japan)
- 8:30 Jacobi Like Algorithm for Non-Orthogonal Joint Diagonalization of Hermitian Matrices
- 8:50 Alternating Direction Method of Multipliers for Non-Negative Matrix Factorization with the Beta-Divergence
- 9:10 Non-negative Source-Filter Dynamical System for Speech Enhancement
- 9:30 Analyzing Data into Quantized Components
- 9:50 An efficient entropy rate estimator for complex-valued signal processing: Application to ICA
- 10:10 Blind qubit state disentanglement with quantum processing: principle, criterion and algorithm using measurements along two directions
IFS-L2: Forensics, Biometrics, and Privacy
Room: Volta
Chairs: Pedro Comesaña (Universidad de Vigo, Spain), Anthony T S Ho (University of Surrey, United Kingdom)
- 8:30 A Video Forensic Technique for Detecting Frame Deletion and Insertion
- 8:50 Guided filtering for PRNU-based localization of small-size image forgeries
- 9:10 Printer Identification from Micro-metric Scale Printing
- 9:30 The Role of Permutation Coding in Minimum-distortion Perfect Counterforensics
- 9:50 Joint kernel collaborative representation on tensor manifold for face recognition
- 10:10 Privacy-Preserving Function Computation by Exploitation of Friendships in Social Networks
SLTC-P17: Speech Analysis and Coding
Room: Poster Area 1
Chair: Tom Bäckström (Friedrich-Alexander University Erlangen-Nürnberg & Fraunhofer IIS, Germany)
- SLTC-P17.1 Sparse Representation Based on a Bag of Spectral Exemplars for Acoustic Event Detection
- SLTC-P17.2 Robust Full-band Adaptive Sinusoidal Analysis and Synthesis of Speech
- SLTC-P17.3 An Adaptive Time-Frequency Analysis Scheme for Improved Real-Time Speech Enhancement
- SLTC-P17.4 A Fixed Dimension and Perceptually based Dynamic Sinusoidal Model of Speech
- SLTC-P17.5 Energy-Constrained Minimum Variance Response Filter for Robust Vowel Spectral Estimation
- SLTC-P17.6 Long audio alignment for automatic subtitling using different phone-relatedness measures
- SLTC-P17.7 Gaussian mixture linear prediction
- SLTC-P17.8 Time Varying Linear Prediction using sparsity constraints
- SLTC-P17.9 Design of Optimal Wavelets for Detecting Impulse Noise in Speech
- SLTC-P17.10 Pitch Enhancement Motivated by Rate-Distortion Theory
- SLTC-P17.11 Intra-Predictive Switched Split Vector Quantization of Speech Spectra
- SLTC-P17.12 Estimating Speaker Height and Subglottal Resonances Using MFCCs and GMMs
- SLTC-P17.13 Frequency warping using subglottal resonances: complementarity with VTLN and robustness to additive noise
- SLTC-P17.14 Shift-Invariant Features for Speech Activity Detection in Adverse Radio-Frequency Channel Conditions
SLTC-P18: Adaptation in Speech Recognition
Room: Poster Area 2
Chair: Mike Seltzer (Microsoft Research, USA)
- SLTC-P18.1 Using contextual information in Joint Factor Eigenspace MLLR for speech recognition in diverse scenarios
- SLTC-P18.2 Regularized Constrained Maximum Likelihood Linear Regression for Speech Recognition
- SLTC-P18.3 Two-Stage Speaker Adaptation in Subspace Gaussian Mixture Models
- SLTC-P18.4 Deep Neural Network Trained with Speaker Representation for Speaker Normalization
- SLTC-P18.5 I-vector-based Speaker Adaptation of Deep Neural Networks for French Broadcast Audio Transcription
- SLTC-P18.6 Direct Adaptation of Hybrid DNN/HMM Model for Fast Speaker Adaptation in LVCSR Based on Speaker Code
- SLTC-P18.7 Investigation of unsupervised adaptation of DNN acoustic models with filter bank input
- SLTC-P18.8 Speaker Adaptive Training using Deep Neural Networks
- SLTC-P18.9 Cache based Recurrent Neural Network Language Model Inference for First Pass Speech Recognition
- SLTC-P18.10 Singular Value Decomposition Based Low-footprint Speaker Adaptation and Personalization for Deep Neural Network
- SLTC-P18.11 Real-time one-pass decoding with recurrent neural network language model for speech recognition
- SLTC-P18.12 Constrained MLE-based speaker adaptation with L1 regularization
- SLTC-P18.13 Training Time Reduction and Performance Improvements from Multilingual Techniques on the Babel ASR Task
- SLTC-P18.14 Domain Adaptation for Parsing in Automatic Speech Recognition
SPTM-P14: Adaptive Systems - Algorithms, Analyses and Applications
Room: Poster Area 3
Chair: Paulo Diniz (UniversidadeFederal do Rio de Janeiro, Brazil)
- SPTM-P14.1 Mean-square performance of the hyperslab-based adaptive projected subgradient method
- SPTM-P14.2 Set-Membership Adaptive Constrained Constant Modulus Reduced-Rank Algorithm for Beamforming
- SPTM-P14.3 Statistical Analysis of Jointly-Optimized GSC Implementations of Beamformer-Assisted Acoustic Echo Cancelers
- SPTM-P14.4 Stability and MSE Analyses of Affine Projection Algorithms for Sparse System Identification
- SPTM-P14.5 Sequential Bayesian learning in linear networks with random decision making
- SPTM-P14.6 Adjustment of Combination Weights Over Adaptive Diffusion Networks
- SPTM-P14.7 On the Gradient Descent Localization of Radioactive Sources
- SPTM-P14.8 Tracking Complex-Valued Multicomponent Chirp Signals Using a Complex Notch Filter with Adaptive Bandwidth and Frequency Parameters
- SPTM-P14.9 Sparsity-Aware Adaptive Algorithms Based on Alternating Optimization and Shrinkage
- SPTM-P14.10 A Quaternion Least Mean Phase Estimator
- SPTM-P14.11 Adaptive Widely Linear Reduced-Rank Beamforming based on Joint Iterative Optimization
SPCOM-P10: Distributed and sparse signal processing with applications
Room: Poster Area 4
Chair: Roberto López-Valcarce (Universidad de Vigo, Spain)
- SPCOM-P10.1 Sparse adaptive multipath tracking for low bandwidth ranging applications
- SPCOM-P10.2 Robust Sparse Channel Estimation for OFDM System using an Iterative Algorithm Based on Complex Median
- SPCOM-P10.3 Distributed support detection of jointly sparse signals
- SPCOM-P10.4 Distributed Quantization for Compressed Sensing
- SPCOM-P10.5 Adaptive Distributed Compressed Sensing for Dynamic High-Dimensional Hypothesis testing
- SPCOM-P10.6 Compressed Acquisition and Progressive Reconstruction of Multi-Dimensional Correlated Data in Wireless Sensor Networks
- SPCOM-P10.7 Recovering Signals with Variable Sparsity Levels from the Noisy 1-Bit Compressive Measurements
- SPCOM-P10.8 Estimation Models for Nonuniformly Sampled Signals - Application to Multiple Delay Estimation
- SPCOM-P10.9 Asymptotic Analysis of Failed Recovery Probability in a Distributed Wireless Storage System with Limited Sum Storage Capacity
- SPCOM-P10.10 A stochastic approximation approach to load shedding in power networks
- SPCOM-P10.11 Sparsity-Aware Channel Estimation with Contaminated Pilot Sequence
SPCOM-P11: Estimation in communication systems
Room: Poster Area 5
Chair: Chong-Yung Chi (National Tsing Hua University, Taiwan)
- SPCOM-P11.1 Fast Time-Varying Channel Estimation Method for LTE SC-FDMA Systems
- SPCOM-P11.2 Flat Fading Channel Estimation Based On Dirty Paper Coding
- SPCOM-P11.3 Channel Estimation for LTE and LTE-A MU-MIMO Uplink with A Narrow Transmission Band
- SPCOM-P11.4 New Subspace-Based Blind Channel Estimation for Orthogonally Coded MIMO-OFDM Systems
- SPCOM-P11.5 Robust Joint CFO and Fast Time-Varying Channel Tracking for MIMO-OFDM Systems
- SPCOM-P11.6 Training Signal Design for Channel Estimation in Massive MIMO Systems
- SPCOM-P11.7 Ziv-Zakai Lower Bound for UWB based TOA Estimation with Unknown Interference
- SPCOM-P11.8 A Decentralized Framework for Linear Coherent Estimation with Spatial Collaboration
- SPCOM-P11.9 One-Shot Blind CFO Estimation for OFDM with Multi-Antenna Receiver
- SPCOM-P11.10 TDOA/AOD/AOA Localization in NLOS Environments
- SPCOM-P11.11 Maximum Likelihood SNR Estimation over Time-Varying Flat-Fading SIMO Channels
IVMSP-P11: Video Segmentation and Tracking
Room: Poster Area 6
Chair: Andrea Cavallaro (Queen Mary, University of London, United Kingdom)
- IVMSP-P11.1 Video background subtraction using semi-supervised robust matrix completion
- IVMSP-P11.2 Visual Object Tracking Via Random Ferns based Classification
- IVMSP-P11.3 A Clustering Approach for Detecting Moving Objects Captured by a Moving Aerial Camera
- IVMSP-P11.4 Multiple Hypotheses Data Association Propagation for Robust Monocular-based SLAM Algorithms
- IVMSP-P11.5 Visual Tracking Using Blind Source Separation for Mixed Images
- IVMSP-P11.6 Automatic Foreground Extraction in Video
- IVMSP-P11.7 An Integrated System for Object Tracking, Detection, and Online Learning with Real-Time RGB-D Video
- IVMSP-P11.8 Vehicle Speed Estimation by License Plate Detection and Tracking
- IVMSP-P11.9 Online co-training ranking SVM for visual tracking
- IVMSP-P11.10 Optical Flow Estimation Using Approximate Nearest Neighbor Field Fusion
- IVMSP-P11.11 Parallel Particle-PHD filter
- IVMSP-P11.12 Fast Shot Segmentation Combining Global and Local Visual Descriptors
- IVMSP-P11.13 A robust, precise and flexible tracking algorithm based on IMS and SWAD
- IVMSP-P11.14 An I-Vector Based Descriptor for Alphabetical Gesture Recognition
BISP-P7: Medical image reconstruction I
Room: Poster Area 7
Chair: Yoram Bresler (University of Illinois, Urbana-Champaign. USA, USA)
- BISP-P7.1 Compressed Sensing for Magnetic Resonance Images with Phase Variations
- BISP-P7.2 X-Ray Image Contrast Enhancement Based On Tissue Attenuation
- BISP-P7.3 Volume Visualization Using Sparse Nonparametric Support Vector Machines and Harmonic Colors
- BISP-P7.4 BM3D MRI denoising equipped with Noise Invalidation technique
- BISP-P7.5 Hull Detection Based On Largest Empty Sector Angle with application to analysis of real time MR images
- BISP-P7.6 Lossless Compression of Medical Images based on HEVC Intra Coding
- BISP-P7.7 A multi-view approach to Consensus Clustering in multi-modal MRI
- BISP-P7.8 Enhanced Retinal Image Registration Accuracy using Expectation Maximisation and Variable Bin-sized Mutual Information
- BISP-P7.9 Data Adaptive Estimation of Transversal Blood Flow Velocities
AASP-P9: Noise and Room Acoustics Control, Audio Source Separation II, Audio Systems
Room: Poster Area 8
Chair: Nordholm Sven (Curtin University of Technology, Australia)
- AASP-P9.1 Joint Time-Domain Reshaping and Frequency-Domain Equalization of Room Impulse Responses
- AASP-P9.2 Steady-state Analysis of Biased Filtered-x Algorithms for Adaptive Room Equalization
- AASP-P9.3 A Novel Decorrelation Approach for Multichannel System Identification
- AASP-P9.4 Sparsity-Inducing Modified Filtered-X Affine Projection Algorithms for Active Noise Control
- AASP-P9.5 New Feedback Active Noise Control System with Improved Performance
- AASP-P9.6 Deep Stacking Networks with Time Series for Speech Separation
- AASP-P9.7 Speech-guided source separation using a pitch-adaptive guide signal model
- AASP-P9.8 Multichannel Audio Separation by Direction of Arrival Based Spatial Covariance Model and Non-Negative Matrix Factorization
- AASP-P9.9 Hybrid Model and Structured Sparsity for Under-Determined Convolutive Audio Source Separation
- AASP-P9.10 Phase and level difference fusion for robust multichannel source separation
- AASP-P9.11 Multi-channel IIR filtering of audio signals using a GPU
- AASP-P9.12 Equalization of excursion and current-dependent nonlinearities in loudspeakers
- AASP-P9.13 Hardware and algorithms for ultrasonic depth imaging
- AASP-P9.14 Audio Packet Loss Concealment Using Spectral Motion
MLSP-P6: Clustering, Factorizations & Feature Selection
Room: Poster Area 9
Chair: Raviv Raich (Oregon State University, USA)
- MLSP-P6.1 Feature selection based on Survival Cauchy-Schwartz mutual information
- MLSP-P6.2 Robust Feature Learning by Stacked Autoencoder with Maximum Correntropy Criterion
- MLSP-P6.3 Piecewise constant Nonnegative matrix factorization
- MLSP-P6.4 M-N scatter plots technique for evaluating varying-size clusters and setting the parameters of Bi-CoPaM and UNCLES methods
- MLSP-P6.5 An initialization strategy for the dictionary learning problem
- MLSP-P6.6 Deflation Method for CANDECOMP/PARAFAC Tensor Decomposition
- MLSP-P6.7 Clustering of Time Series Using a Hierarchical Linear Dynamical System
- MLSP-P6.8 First Order Methods for Robust Non-negative Matrix Factorization for Large Scale Noisy Data
- MLSP-P6.9 Multiple Kernel Interpolation for Inverting Non-Linear Dimensionality Reduction and Dimension Estimation
- MLSP-P6.10 Feature Reduction Based on Sum-of-SNR (SOSNR) Optimization
- MLSP-P6.11 Neighborhood selection for thresholding based subspace clustering
- MLSP-P6.12 On Fast Algorithms for Orthogonal Tucker Decomposition
- MLSP-P6.13 Discriminative Exemplar Clustering
SAM-P6: Compressive and Physics-Based Methods
Room: Poster Area 10
Chair: Lee Swindlehurst (University of California at Irvine, USA)
- SAM-P6.1 On the estimation of Grid Offsets in CS-based Direction-of-Arrival Estimation
- SAM-P6.2 An efficient sub-nyquist receiver architecture for spectrum blind reconstruction and direction of arrival estimation
- SAM-P6.3 Accurate Reconstruction Of Rain Field Maps From Commercial Microwave Networks Using Sparse Field Modeling
- SAM-P6.4 Fast and Stable Recovery of Approximately Low Multilinear Rank Tensors From Multi-Way Compressive Measurements
- SAM-P6.5 Improved Compressed Sensing Radar by Fusion with Matched Filtering
- SAM-P6.6 Optimal Trajectory Design For a DToA Based Multi-Robot Angle of Arrival Estimation System for Rescue Operations
- SAM-P6.7 Wavenumber tracking in a low resolution frequency-wavenumber representation using particle filtering
- SAM-P6.8 Design of a robust open spherical microphone array
- SAM-P6.9 Tactile Tomographic Fluid-Flow Imaging with a Robotic Whisker Array
- SAM-P6.10 Outlier removal for improved source estimation in atmospheric inverse problems
- SAM-P6.11 Near-Optimal Source Placement For Linear Physical Fields
- SAM-P6.12 Physics-Based Sea Clutter Model for Improved Detection of Low Radar Cross-Section Targets
- SAM-P6.13 Source counting in speech mixtures using a variational EM approach for complex Watson mixture models
- SAM-P6.14 Sparsity-Aware Sensor Selection: Centralized and Distributed Algorithms
10:30 AM - 11:00 AM
Coffee break
11:00 AM - 1:00 PM
SLTC-L11: Deep Learning in Speech Recognition
Room: Cavaniglia
Chairs: Li Deng (Microsoft Research, USA), Tara Sainath (IBM TJ Watson Research Center, USA)
- Improvements to Filterbank and Delta Learning Within A Deep Neural Network Framework
- Sequence Classification Using the High-Level Features Extracted from Deep Neural Networks
- Improving deep neural networks for LVCSR using dropout and shrinking structure
- Exploring One Pass Learning For Deep Neural Network Training With Averaged Stochastic Gradient Descent
- Accounting for the Residual Uncertainty of Multi-Layer Perceptron based Features
- Unsupervised Domain Adaptation for Deep Neural Network Based Voice Activity Detection
IVMSP-L5: Image Indexing and Retrieval
Room: Basilica
Chair: Constantine Kotropoulos (Aristotle University of Thessaloniki, Greece)
- 11:00 Low-cost multi-camera object matching
- 11:20 Extended-Bag-of-Features for Translation, Rotation, and Scale-Invariant Image Retrieval
- 11:40 Image Retrieval Based on Spatial Context with Relaxed Gabriel Graph Pyramid
- 12:00 Beyond "Project and Sign" for Cosine Estimation with Binary Codes
- 12:20 Visual Reranking with improved image graph
- 12:40 Simultaneous image tagging and geo-location prediction within hypergraph ranking framework
BISP-L3: Medical image reconstruction II
Room: Polveriera
Chairs: Mathews Jacob (University of Iowa, USA), Yves Wiaux (Heriot Watt University, United Kingdom)
- 11:00 Compressed Quantitative MRI: Bloch Response Recovery through Iterated Projection
- 11:20 Joint recovery of under sampled signals on a manifold: application to free breathing cardiac MRI
- 11:40 Model-Based Iterative Reconstruction for Synchrotron X-Ray Tomography
- 12:00 Tomographic Reconstruction with Adaptive Sparsifying Transforms
- 12:20 Compressed 3D Ultrasound Imaging with 2D Arrays
- 12:40 Improved MRI Reconstruction via Non-Convex Elastic Net
AASP-L5: Recent Topics on Audio Coding
Room: Scherma
Chairs: Akihiko K. Sugiyama (NEC Corporation, Japan), Vinay Melkote (Dolby Laboratories, USA)
- 11:00 Nonlinear Estimation of Missing $\Delta$LSF Parameters by a Mixture of Dirichlet Distributions
- 11:20 Lossless Audio Compression in the New IEEE Standard for Advanced Audio Coding
- 11:40 Sinusoidal Substitution - An Integrated Parametric Tool for Enhancement of Transform-Based Perceptual Audio Coders
- 12:00 A posteriori voiced / unvoiced probability estimation based on a sinusoidal model
- 12:20 Transform-domain Decorrelation in Dolby Digital Plus
- 12:40 Improved Low-Delay MDCT-Based Coding of Both Stationary and Transient Audio Signals
SS12: Deep Learning for Music
Room: Teatrino
Chairs: Eric Battenberg (Gracenote, Inc., USA), Juan Bello (New York University, USA), Erik Schmidt (Pandora Media, Inc., USA)
- 11:00 Improved Music Feature Learning With Deep Neural Networks
- 11:20 End-to-end learning for music audio
- 11:40 Exploiting long-term temporal dependencies in NMF using recurrent neural networks with application to source separation
- 12:00 From Music Audio to Chord Tablature: Teaching Deep Convolutional Networks to Play Guitar
- 12:20 Improved Musical Onset Detection with Convolutional Neural Networks
- 12:40 A Deep Representation for Invariance And Music Classification
SPCOM-L6: Network Perspectives
Room: Volta
Chair: Timothy N. Davidson (McMaster University, Canada)
- 11:00 Performance of Partial Zero-forcing Beamforming in Large Random Spectrum Sharing Networks
- 11:20 An Accurate and Efficient Analysis of a MBSFN Network
- 11:40 A Statistical Approach to Interference Reduction in Distributed Large-scale Antenna Systems
- 12:00 Analysis of RF Energy Harvesting in Large-Scale Networks Using Absorption Function
- 12:20 Transmission Mode Selection for Network-Assisted Device to Device Communication: A Levy-Bandit Approach
- 12:40 Distributed energy-efficient power optimization in cellular relay networks with minimum rate constraints
SLTC-P19: Reduction of Noise in Speech
Room: Poster Area 1
Chair: Israel Cohen (Technion, Israel)
- SLTC-P19.1 Noise-robust detection of peak-clipping in decoded speech
- SLTC-P19.2 Speech Enhancement Using a Modulation Domain Kalman Filter Post-processor With a Gaussian Mixture Noise Model
- SLTC-P19.3 Mask-based Enhancement for Very Low Quality Speech
- SLTC-P19.4 A Two-Stage Approach for Improving the Perceptual Quality of Separated Speech
- SLTC-P19.5 A Feature Study for Classification-based Speech Separation at Very Low Signal-to-noise Ratio
- SLTC-P19.6 On the EM Algorithm for the Estimation of Speech AR Parameters in Noise
- SLTC-P19.7 Parametric Multichannel Noise Reduction Algorithm Utilizing Temporal Correlations in Reverberant Environment
- SLTC-P19.8 Speech Enhancement Combining Statistical Models and NMF with Update of Speech and Noise Bases
- SLTC-P19.9 Noise Reduction in the Time Domain using Joint Diagonalization
- SLTC-P19.10 Single Microphone Wind Noise PSD Estimation Using Signal Centroids
- SLTC-P19.11 Binaural Noise PSD Estimation for Binaural Speech Enhancement
- SLTC-P19.12 A negentropy based adaptive line enhancer for single-channel noise reduction at low SNR conditions
- SLTC-P19.13 Iterative Closed-Loop Phase-Aware Single-Channel Speech Enhancement
SLTC-P20: Spoken Term Detection I
Room: Poster Area 2
Chair: Satoshi Nakamura (Nara Institute of Science and Technology, Japan)
- SLTC-P20.1 Discriminative score normalization for keyword search decision
- SLTC-P20.2 I-vector Based Language Modeling for Spoken Document Retrieval
- SLTC-P20.3 Rescoring Confusion Networks For Keyword Search
- SLTC-P20.4 Zero-resource spoken term detection using hierarchical graph-based similarity search
- SLTC-P20.5 Translating TED Speeches by Recurrent Neural Network based Translation Model
- SLTC-P20.6 An autoencoder with bilingual sparse features for improved statistical machine translation
- SLTC-P20.7 Out-of-Vocabulary Word Detection in a Speech-to-Speech Translation System
- SLTC-P20.8 Intra-content term weighting for Topic Segmentation
- SLTC-P20.9 Limited Resource Term Detection for Effective Topic Identification of Speech
- SLTC-P20.10 Effective Representations for Leveraging Language Content in Multimedia Event Detection
- SLTC-P20.11 Use of Articulatory Bottle-Neck Features for Query-by-Example Spoken Term Detection in Low Resource Scenarios
- SLTC-P20.12 Unsupervised Query-by-Example Spoken Term Detection using Segment-based Bag of Acoustic Words
- SLTC-P20.13 Calibration and multiple system fusion for spoken term detection using linear logistic regression
- SLTC-P20.14 Feature Fusion for High-Accuracy Keyword Spotting
SPTM-P15: Sparsity-Aware Learning and Reconstruction
Room: Poster Area 3
Chair: Bhaskar Rao (University of California, San Diego, USA)
- SPTM-P15.1 Projection onto the Cosparse Set is NP-hard
- SPTM-P15.2 Group-sparse Matrix Recovery
- SPTM-P15.3 Overcomplete Sparsifying Transform Learning Algorithm using a Constrained Least Squares Approach
- SPTM-P15.4 On Recovery of Block Sparse Signals from Multiple Measurements
- SPTM-P15.5 Information alignment for consensus with interference
- SPTM-P15.6 Efficient Convolutional Sparse Coding
- SPTM-P15.7 Subspace metrics for multivariate dictionaries and application to EEG
- SPTM-P15.8 Nested Sparse Bayesian Learning for Block-Sparse Signals with Intra-Block Correlation
- SPTM-P15.9 Dynamic Sparse Coding with Smoothing Proximal Gradient Method
- SPTM-P15.10 Analysis SimCO: A New Algorithm for Analysis Dictionary Learning
- SPTM-P15.11 Iterative log thresholding
- SPTM-P15.12 High Resolution Sparse Estimation of Exponentially Decaying Signals
- SPTM-P15.13 Flexible Parallel Algorithms for Big Data Optimization
SPTM-P16: Topics in Adaptive Signal Processing
Room: Poster Area 4
Chair: Cassio Lopes (University of São Paulo, Brazil)
- SPTM-P16.1 Sparse LMS via online linearized Bregman iteration
- SPTM-P16.2 Combination Coefficients for Fastest Convergence of Distributed LMS Estimation
- SPTM-P16.3 Distributed Diffusion-based LMS for Node-Specific Parameter Estimation over Adaptive Networks
- SPTM-P16.4 Learning Distributed Jointly Sparse Systems by Collaborative LMS
- SPTM-P16.5 Robust Distributed Detection Over Adaptive Diffusion Networks
- SPTM-P16.6 Sparse Constraint Affine Projection Algorithm with Parallel Implementation and Application in Compressive Sensing
- SPTM-P16.7 Convergence analysis of kernel LMS algorithm with pre-tuned dictionary
- SPTM-P16.8 There's plenty of room at the bottom: Incremental combinations of sign-error LMS filters
- SPTM-P16.9 Efficient Learning by Consensus over Regular Networks
SPCOM-P12: Spectrum sensing and cognitive radio
Room: Poster Area 5
Chair: Dimitris A. Pados (The State University of New York at Buffalo, USA)
- SPCOM-P12.1 The Myopic Solution of the Multi-Armed Bandit Compressive Spectrum Sensing Problem
- SPCOM-P12.2 Distributed Wideband Spectrum Sensing for Cognitive Radio Networks
- SPCOM-P12.3 Maximum Eigenvalue Detection for Spectrum Sensing under Correlated Noise
- SPCOM-P12.4 Mobile Distributed Compressive Sensing for Spectrum Sensing
- SPCOM-P12.5 Gerschgorin Disk-based Robust Spectrum Sensing for Cognitive Radio
- SPCOM-P12.6 Joint Sensing and Resource Allocation for Underlay Cognitive Radios
- SPCOM-P12.7 A Non-Periodic Sensing Strategy for Improved Throughput in Cognitive Radio Networks
- SPCOM-P12.8 Cognitive Transmit Beamforming from Binary Link Quality Feedback for Point to Point MISO channels
- SPCOM-P12.9 Graph-Based Robust Resource Allocation for Cognitive Radio Networks
- SPCOM-P12.10 Opportunistic User Scheduling in MIMO Cognitive Radio Networks
- SPCOM-P12.11 Robust Beamforming with Decentralized Interference Coordination in Cognitive Radio Networks
- SPCOM-P12.12 Interference Shaping Constraints for Underlay MIMO Interference Channels
- SPCOM-P12.13 Intervention Framework for Counteracting Collusion in Spectrum Leasing Systems
- SPCOM-P12.14 Channel-Aware Distributed Dynamic Spectrum Access via Learning-Based Heterogeneous Multi-channel Auction
IVMSP-P12: Video coding
Room: Poster Area 6
Chair: Beatrice Pesquet-Popescu (Télécom ParisTech, France)
- IVMSP-P12.1 A convex-optimization framework for frame-level optimal rate allocation in predictive video coding
- IVMSP-P12.2 Low-Delay Window-Based Rate Control Scheme for Video Quality Optimization in Video Encoder
- IVMSP-P12.3 Region-of-interest Based Rate Control Scheme for High Efficiency Video Coding
- IVMSP-P12.4 SSIM-Based Rate-Distortion Optimization in H.264
- IVMSP-P12.5 Palette-based Compound Image Compression in HEVC By Exploiting Non-Local Spatial Correlation
- IVMSP-P12.6 HEVC Decoder Acceleration on Multi-core X86 Platform
- IVMSP-P12.7 A Low-Complexity and Lossless Reference Frame Encoder Algorithm for Video Coding
- IVMSP-P12.8 An Efficient Motion Vector Prediction Method for Avoiding AMVP Data Dependency for HEVC
- IVMSP-P12.9 Adaptive Re-Quantization For High Dynamic Range Video Compression
- IVMSP-P12.10 Joint Inter-Intra Prediction Based on Mode-Variant and Edge-Directed Weighting Approaches in Video Coding
- IVMSP-P12.11 Weighted-prediction-based color gamut scalability extension for the H.265/HEVC video codec
- IVMSP-P12.12 Smart Decoder: A New Paradigm for Video Coding
IFS-P3: Multimedia Encryption, Secure Computations, and Data Hiding
Room: Poster Area 7
Chair: Sen-ching Samson Cheung (University of Kentucky, USA)
- IFS-P3.1 A new lossy compression scheme for encrypted gray-scale images
- IFS-P3.2 Formulation of visual secret sharing schemes encrypting multiple images
- IFS-P3.3 Security of audio secret sharing scheme encrypting audio secrets with bounded shares
- IFS-P3.4 Efficient Multi-party Computation with Collusion-deterred Secret Sharing
- IFS-P3.5 Secure Multi-Party Consensus Gossip Algorithms
- IFS-P3.6 On the Performance Analysis of Data Fusion Schemes with Byzantines
- IFS-P3.7 Adjusting Bit-stream Video Watermarking Systems to Cope with HTTP Adaptive Streaming Transmission
- IFS-P3.8 Efficient reversible data hiding based on two-dimensional pixel-intensity-histogram modification
- IFS-P3.9 Improved Control for Low Bit-rate Reversible Watermarking
- IFS-P3.10 A New Method for Image Reconstruction Using Self-Embedding
- IFS-P3.11 Source-Channel Coding Approach to Generate Tamper-Proof Images
AASP-P10: Microphone Array Processing II, Music Analysis and Synthesis II
Room: Poster Area 8
Chair: Augusto Sarti (Politecnico di Milano, Italy)
- AASP-P10.1 Power-based Signal-to-Diffuse Ratio Estimation using Noisy Directional Microphones
- AASP-P10.2 Extended Kalman Filter with Probabilistic Data Association for Multiple Non-Concurrent Speaker Localization in Reverberant Environments
- AASP-P10.3 Source number estimation in reverberant conditions via full-band weighted, adaptive fuzzy c-means clustering
- AASP-P10.4 Calibration of distributed sound acquisition systems using TOA measurements from a moving acoustic source
- AASP-P10.5 Sparse Cepstral Codes and Power Scale for Instrument Identification
- AASP-P10.6 True Discrete Cepstrum: an accurate and smooth spectral envelope estimation for music processing
- AASP-P10.7 Timbre Replacement of Harmonic and Drum Components for Music Audio Signals
- AASP-P10.8 Phase Constrained Complex NMF: Separating Overlapping Partials in Mixtures of Harmonic Musical Sources
- AASP-P10.9 On the Reduction of False Positives in Singing Voice Detection
- AASP-P10.10 A Nonlinear Second-Order Digital Oscillator For Virtual Acoustic Feedback
- AASP-P10.11 Music Signal Separation Based on Bayesian Spectral Amplitude Estimator with Automatic Target Prior Adaptation
- AASP-P10.12 A Novel Cepstral Representation For Timbre Modeling Of Sound Sources In Polyphonic Mixtures
DISPS-P2: Implementations of DSP Systems and Applications
Room: Poster Area 9
Chair: Woon Seng Gan (Nanyang Technological University, Singapore)
- DISPS-P2.1 IEEE 802.11ac MIMO Transmitter Baseband Processing on Customized VLIW Processor
- DISPS-P2.2 Scalable, Efficient ASICs for the Square Kilometre Array: from A/D Conversion to Central Correlation
- DISPS-P2.3 x1000 Real-time Phoneme Recognition VLSI Using Feed-forward Deep Neural Networks
- DISPS-P2.4 A High Throughput LDPC Decoder using a Mid-range GPU
- DISPS-P2.5 Using the GPU for fast symmetry-based dense stereo matching in high resolution images
- DISPS-P2.6 Barometric and GPS Altitude Sensor Fusion
- DISPS-P2.7 Boosted Multi-class Object Detection with Parallel Hardware Implementation for Real-Time Applications
- DISPS-P2.8 GPU based implementation of multichannel adaptive room equalization
- DISPS-P2.9 Australian SKA Pathfinder: Digital Signal Processing Implementation and Early Engineering Test Array Results
- DISPS-P2.10 Multi-core software architecture for the scalable HEVC decoder
- DISPS-P2.11 Fast And Efficient Real-Time GPU Based Implementation of Wave Field Synthesis
- DISPS-P2.12 Fast Software Polar Decoders
- DISPS-P2.13 DSP Implementation of SQRT(M)-Best Rotated QAM Soft-Demapper
- DISPS-P2.14 A fast architecture for finding maximum (or minimum) values in a set
SAM-P7: Sensor and Relay Networks
Room: Poster Area 10
Chair: Shahram ShahbazPanahi (University of Ontario Institute of Technology, Canada)
- SAM-P7.1 A Modified broadcast strategy for distributed signal estimation in a wireless sensor network with a tree topology
- SAM-P7.2 A gossiping approach to sampling clock synchronization in wireless acoustic sensor networks
- SAM-P7.3 Distributed Total Least Squares Estimation over Networks
- SAM-P7.4 Performance-Energy Tradeoffs in Cutset Wireless Sensor Networks
- SAM-P7.5 Optimal Spectrum Leasing and Network Beamforming for Two-Way Relay Networks
- SAM-P7.6 Multi-antenna Relay Network Beamforming Design for Multiuser Peer-to-Peer Communications
- SAM-P7.7 Filter-and-forward relay beamforming using output power minimization
- SAM-P7.8 SINR balancing for non-regenerative two-way relay networks with interference neutralization
- SAM-P7.9 Reduced Order Distributed Particle Filter for Electric Power Grids
- SAM-P7.10 Sensor Fault Detection by Sparsity Optimization
- SAM-P7.11 How Many Bits from How Many Sensors? A Trade-off in Distributed Nearest-Neighbor Learning
- SAM-P7.12 Bayesian Design of Decentralized Hypothesis Testing Under Communication Constraints
- SAM-P7.13 Generalized Quadratically Constrained Quadratic Programming for Signal Processing
1:00 PM - 2:45 PM
Lunch Time
2:45 PM - 3:45 PM
PT4: Plenary Talk: Synchronization and detectability in nonlinear networks and biology (Room Cavaniglia)
Keynote speaker: Jean-Jacques Slotine (MIT, USA)
3:45 PM - 4:15 PM
Coffee break
4:15 PM - 6:15 PM
SLTC-L12: Neural network ASR
Room: Cavaniglia
Chairs: Daniel Povey (Johns Hopkins University, USA), Frank Seide (Microsoft Research Asia, P.R. China)
- 4:15 An auto-encoder based approach to unsupervised learning of subword units
- 4:35 Multilingual Deep Neural Network Based Acoustic Modeling For Rapid Language Adaptation
- 4:55 Fine context, low-rank, softplus deep neural networks for mobile speech recognition
- 5:15 Investigation of Maxout Networks For Speech Recognition
- 5:35 Adaptation of Multilingual Stacked Bottle-Neck Neural Network Structure for New Language
- 5:55 On Modeling Context-dependent Clustered States: Comparing HMM/GMM, Hybrid HMM/ANN and KL-HMM Approaches
SPTM-L9: Sparsity-Aware Learning
Room: Basilica
Chairs: Mario A. T. Figueiredo (Instituto Superior Técnico, Portugal), Georgios B. Giannakis (University of Minnesota, USA)
- 4:15 Sparse Dictionary Learning from 1-bit Data
- 4:35 Estimation of Simultaneously Structured Covariance Matrices from Quadratic Measurements
- 4:55 Robust Binary Fused Compressive Sensing using Adaptive Outlier Pursuit
- 5:15 Adaptive variational sparse Bayesian estimation
- 5:35 Kernel Selection for Power Market Inference via Block Successive Upper Bound Minimization
- 5:55 A block coordinate descent method of multipliers: Convergence Analysis and Applicaitons
SS13: Non-native Speech Processing
Room: Polveriera
Chairs: Ricardo Gutierrez-Osuna (Texas A&M University, USA), Michael Johnson (Marquette University, USA)
- 4:15 Accent conversion through cross-speaker articulatory synthesis
- 4:35 Accent Rating by Native and Non-native Listeners
- 4:55 Lexical Stress Classification for Language Learning Using Spectral and Segmental Features
- 5:15 Adaptive and Discriminative Modeling for Improved Mispronunciation Detection
- 5:35 Phonological Modeling of Mispronunciation Gradations in L2 English Speech of L1 Chinese Learners
- 5:55 The Electromagnetic Articulography Mandarin Accented English (EMA-MAE) Corpus of Acoustic and 3D Articulatory Kinematic Data
SAM-L4: SAM for Wireless Communications
Room: Scherma
Chairs: Martin Haardt (Ilmenau University of Technology, Germany), Sergiy A. Vorobyov (Aalto University & University of Alberta on leave, Finland)
- SAM-L4.1 4:15 Multiuser downlink beamforming with interference cancellation using a SDP-Based Branch-and-Bound Algorithm
- SAM-L4.2 4:35 Performance Analysis of Max-SINR Algorithm Under CSI Mismatch
- SAM-L4.3 4:55 Optimal Decision Threshold for Eigenvalue-Based Spectrum Sensing Techniques
- SAM-L4.4 5:15 Optimal MIMO Broadcasting over Time-Varying Wireless Channels for Energy Harvesting Transmitter with Non-Ideal Circuit Power
- SAM-L4.5 5:35 Optimum Discrete Single Group Multicast Beamforming
- SAM-L4.6 5:55 Blind Spectra Separation and Direction Finding for Cognitive Radio Using Temporal Correlation-domain ESPRIT
SPCOM-L7: Power Systems Management and Smart Grid
Room: Teatrino
Chairs: Timothy N. Davidson (McMaster University, Canada), Zhi-Quan Luo (University of Minnesota, USA)
- 4:15 Joint Day-Ahead Power Procurement and Load Scheduling Using Stochastic Alternating Direction Method of Multipliers
- 4:35 Non-stationary Demand Side Management Method for Smart Grids
- 4:55 Asynchronous Alternating Direction Method of Multipliers Applied to the Direct-Current Optimal Power Flow Problem
- 5:15 An Off-line Optimization Approach for Online Energy Storage Management in Microgrid System
- 5:35 Intertemporal Trading Economy Model for Smart Grid Household Energy Consumption
- 5:55 Integrating Energy Storage into the Smart Grid: A Prospect Theoretic Approach
IVMSP-L6: Image Formation
Room: Volta
Chair: Enrico Magli (Politecnico di Torino, Italy)
- 4:15 Non-uniform sampling and Gaussian process regression in transport of intensity phase imaging
- 4:35 Compressive spectral imaging with colored-patterned detectors
- 4:55 Compressive Hyperspectral Imaging Using Progressive Total Variation
- 5:15 Compressive Spectral Imaging based on Colored Coded Apertures
- 5:35 Enhanced Wall Clutter Mitigation For Compressed Through-the-Wall Radar Imaging using Joint Bayesian Sparse Signal Recovery
- 5:55 An unmixing-based method for the analysis of thermal hyperspectral images
SLTC-P21: Spoken Term Detection II
Room: Poster Area 1
Chair: Julia Hirschberg (Columbia University in the City of New York, USA)
- SLTC-P21.1 Unsupervised Spoken Term Detection with Spoken Queries by Multi-level Acoustic Patterns with Varying Model Granularity
- SLTC-P21.2 High-Performance Query-by-Example Spoken Term Detection on the SWS 2013 Evaluation
- SLTC-P21.3 Using Word Burst Analysis to Rescore Keyword Search Candidates on Low-Resource Languages
- SLTC-P21.4 The 2013 BBN Vietnamese Telephone Speech Keyword Spotting System
- SLTC-P21.5 Normalization of Phonetic Keyword Search Scores
- SLTC-P21.6 Automatic Keyword Selection for Keyword Search Development and Tuning
- SLTC-P21.7 Efficient Spoken Term Detection using Confusion Networks
- SLTC-P21.8 Calibration and Fusion of Query-by-Example systems - BUT SWS 2013
- SLTC-P21.9 Multilingual MRASTA Features for Low-resource Keyword Search and Speech Recognition Systems
- SLTC-P21.10 Featherweight Phonetic Keyword Search for Conversational Speech
- SLTC-P21.11 Subword-based Modeling for Handling OOV Words in Keyword Spotting
- SLTC-P21.12 Semi-supervised term-weighted value rescoring for keyword search
- SLTC-P21.13 Recursive Neural Network based Word Topology Model for Hierarchical Phrase-based Speech Translation
SLTC-P22: Voice Conversion
Room: Poster Area 2
Chair: Alan Black (CMU, USA)
- SLTC-P22.1 Can voice conversion be used to reduce non-native accents?
- SLTC-P22.2 Using Bidirectional Associative Memories for Joint Spectral Envelope Modeling in Voice Conversion
- SLTC-P22.3 Voice conversion in time-invariant speaker-independent space
- SLTC-P22.4 Voice Conversion Based on Non-negative Matrix Factorization using Phoneme-categorized Dictionary
- SLTC-P22.5 Audio-Visual Voice Conversion using Noise-Robust Features
- SLTC-P22.6 Regression approaches to perceptual age control in singing voice conversion
- SLTC-P22.7 Non-Parallel Voice Conversion Using Joint Optimization of Alignment by Temporal Context and Spectral Distortion
- SLTC-P22.8 Improving voice quality of HMM-based speech synthesis using voice conversion method
- SLTC-P22.9 Guslar: a framework for automated singing voice correction
- SLTC-P22.10 Pitch Modifications of speech based on an Adaptive Harmonic Model
- SLTC-P22.11 Improvement of Probabilistic Acoustic Tube Model for speech decomposition
- SLTC-P22.12 Enhancing Frequency Shifted Speech Signals in Single Side-band Communication
SPTM-P17: Nonlinear Signal Processing
Room: Poster Area 3
Chair: V. John Mathews (University of Utah, USA)
- SPTM-P17.1 A novel class of BIBO stable recursive nonlinear filters
- SPTM-P17.2 Introducing Legendre Nonlinear Filters
- SPTM-P17.3 Sparse Representations in Nested Non-Linear Models
- SPTM-P17.4 Detection of Nonlinear Mixtures Using Gaussian Processes: Application to Hyperspectral Imaging
- SPTM-P17.5 Nonlinear unmixing of hyperspectral images using a semiparametric model and spatial regularization
- SPTM-P17.6 Perfect periodic sequences for identification of even mirror Fourier nonlinear filters
- SPTM-P17.7 A Robust Kernel Density Estimator Based Mean-Shift Algorithm
- SPTM-P17.8 A particle filtering based kernel HMM predictor
- SPTM-P17.9 Subband Digital Predistorsion based on Indirect Learning Architecture
- SPTM-P17.10 Multi-modal filtering for non-linear estimation
SPTM-P18: Data Driven Methods
Room: Poster Area 4
Chair: Petar M. Djurić (Stony Brook University, USA)
- SPTM-P18.1 Distributed Particle Filtering for Blind Equalization in Receiver Networks using Marginal Non-Parametric Approximations
- SPTM-P18.2 Robust Bootstrap Methods with an Application to Geolocation in Harsh LOS/NLOS Environments
- SPTM-P18.3 An Adaptive Likelihood Fusion Method using Dynamic Gaussian Model for Indoor Target Tracking
- SPTM-P18.4 Independent doubly adaptive rejection Metropolis sampling
- SPTM-P18.5 Efficient Particle-Based Online Smoothing in General Hidden Markov Models
- SPTM-P18.6 Multiple Transition Mode Multiple Target Track-Before-Detect With Partitioned Sampling
- SPTM-P18.7 Particle Filtering in High-Dimensional Systems with Gaussian Approximations
- SPTM-P18.8 An Experimental Implementation of a Particle-Based Dynamic Sensor Steering Method for Tracking and Searching for Space Objects
- SPTM-P18.9 A Poisson series approach to Bayesian Monte Carlo inference for skewed alpha-stable distributions
- SPTM-P18.10 Fast computation of the L1 principal component of real-valued data
- SPTM-P18.11 Estimation of ARMA State Processes by Particle Filtering
- SPTM-P18.12 An Adaptive Population Importance Sampler
- SPTM-P18.13 Monte Carlo Limit Cycle Characterization
- SPTM-P18.14 On The $L^4$ Convergence of Particle Filters with General Importance Distributions
SPCOM-P13: Multicarrier systems
Room: Poster Area 5
Chair: Paolo Banelli (University of Perugia, Italy)
- SPCOM-P13.1 OFDM spectrum sculpting with Active Interference Cancellation: keeping spectral spurs at bay
- SPCOM-P13.2 Short Preamble-based Estimation of Highly Frequency Selective Channels in FBMC/OQAM
- SPCOM-P13.3 Cepstrum based detection and classification of OFDM waveforms
- SPCOM-P13.4 Dynamic Upstream Power Back-off for Mixtures of Vectored and Non-vectored VDSL
- SPCOM-P13.5 Frequency-Shift Filtering for OFDM Recovery in Narrowband Power Line Communications
- SPCOM-P13.6 A parallel processing approach to filterbank multicarrier MIMO transmission under strong frequency selectivity
- SPCOM-P13.7 A Low-Complexity Blind CFO Estimation for OFDM Systems
- SPCOM-P13.8 Receiver Based PAPR Reduction in OFDMA
- SPCOM-P13.9 Sub-Nyquist Sampling of OFDM Signals for Cognitive Radios
- SPCOM-P13.10 An Advanced Multi-Carrier Modulation for Future Radio Systems
- SPCOM-P13.11 Differential Decoding for SFBC OFDM systems in Underwater MIMO Channels
- SPCOM-P13.12 Constant Modulus Algorithm for Peak-to-Average Power Ratio (PAPR) Reduction in MIMO OFDM/A
- SPCOM-P13.13 A Nonlinear Equalization Algorithm for Single-Carrier Block Transmission Systems
IVMSP-P13: Remote Sensing and Seismic Imaging
Room: Poster Area 6
Chair: James Fowler (Mississippi State University, USA)
- IVMSP-P13.1 Effective Small Dim Target Detection by Local Connectedness Constraint
- IVMSP-P13.2 Subspace Vertex Pursuit for Separable Non-negative Matrix Factorization in Hyperspectral Unmixing
- IVMSP-P13.3 Combined Intensity and Coherent Change Detection for Synthetic Aperture Radar
- IVMSP-P13.4 Tomographic Techniques for the Retrieval of Tropospheric Water Vapour Fields by Using Co-Rotating LEO Satellites
- IVMSP-P13.5 Robust Lane Detection & Tracking Based on Novel Feature Extraction and Lane Categorization
- IVMSP-P13.6 Automatic Fault Localization using the Generalized Earth Mover's Distance
- IVMSP-P13.7 Direct Tracking from Compressive Imagers: A Proof of Concept
- IVMSP-P13.8 POLSAR Image Speckle Reduction Based on Sparse Representation and Structure Characteristics
- IVMSP-P13.9 Parameter estimation for instantaneous spectral imaging
- IVMSP-P13.10 3D particle volume tomographic reconstruction based on marked point process: Application to Tomo-PIV in fluid mechanics
IFS-P4: Secure Communications and Key Generation
Room: Poster Area 7
Chair: Jiwu Huang (Shenzhen University, P.R. China)
- IFS-P4.1 Achieving Perfect Secrecy by pdf-Bandlimited Jamming
- IFS-P4.2 A fictitious play-based game-theoretical approach to alleviating jamming attacks for Cognitive radios
- IFS-P4.3 Cryptographically Secure Radios Based on Directional Modulation
- IFS-P4.4 Tandem Distributed Bayesian Detection with Privacy Constraints
- IFS-P4.5 Variable Guard Band Construction to Support Key Reconciliation
- IFS-P4.6 Robust Secret Key Capacity for the MIMO Induced Source Model
- IFS-P4.7 Secret Key Generation from Multiple Cooperative Helpers by Rate Unlimited Public Communication
- IFS-P4.8 Unbiased Random Sequences from Measurements of Poisson Processes
- IFS-P4.9 Helper-less Physically Unclonable Functions and Chip Authentication
- IFS-P4.10 DCT Based Ring Oscillator Physical Unclonable Functions
AASP-P11: Hearing Aids II, Analysis of Acoustic Environments, Animal Sound Analysis
Room: Poster Area 8
Chair: Thushara D. Abhayapala (Australian National University, Australia)
- AASP-P11.1 Howling Detection in Hearing aids Using Discrete Energy Separation Algorithm-2 and Generalized Teager-Kaiser Operator
- AASP-P11.2 Sub-band Feedback Cancellation with Variable Step Sizes for Music Signals in Hearing Aids
- AASP-P11.3 New Insights Into Optimal Acoustic Feedback Cancellation
- AASP-P11.4 A comparison of spectro-temporal representations of audio signals
- AASP-P11.5 Visualization of acoustic pressure and velocity patterns with phase information in the pinna cavities at normal modes
- AASP-P11.6 Randomness and The Reverberation Time, RT60, of Acoustic Responses
- AASP-P11.7 Decimation of Finite-Difference Time-Domain schemes in 1D and 2D boundary-absorbing acoustic model simulations
- AASP-P11.8 Robust Minimum Statistics Project Coefficients Feature For Acoustic Environment Recognition
- AASP-P11.9 A Supervised Signal-To-Noise Ratio Estimation Of Speech Signals
- AASP-P11.10 A refined time-frequency reassignment technique applied to dolphin echolocation signals
- AASP-P11.11 Probabilistic Extraction and Discovery of Fundamental Units in Dolphin Whistles
- AASP-P11.12 New parametric representations of bird sounds for automatic classification
- AASP-P11.13 Bird Species Recognition from Field Recordings using HMM-based Modelling of Frequency Tracks
MLSP-P7: Learning Theory II
Room: Poster Area 9
Chair: Bhaskar Rao (University of California, San Diego, USA)
- MLSP-P7.1 Strong impossibility results for noisy group testing
- MLSP-P7.2 Keops: KErnels Organized into PyramidS
- MLSP-P7.3 Signal inpainting on graphs via total variation minimization
- MLSP-P7.4 Probabilistic Kernel Least Mean Squares Algorithms
- MLSP-P7.5 Stochastic modeling and disaggregation of energy consumption behavior
- MLSP-P7.6 Efficient Unimodality Test In Clustering By Signature Testing
- MLSP-P7.7 Logarithmic Regret Bound Over Diffusion Based Distributed Estimation
- MLSP-P7.8 A saddle point algorithm for networked online convex optimization
- MLSP-P7.9 Sharp Performance Bounds for Graph Clustering via Convex Optimization
- MLSP-P7.10 A quasi-Newton method for large scale support vector machines
- MLSP-P7.11 Ranking 2DLDA Features Based on Fisher Discriminance
- MLSP-P7.12 Epigraphical proximal projection for sparse Multiclass SVM
DISPS-P3: Low-Power Signal Processing
Room: Poster Area 10
Chair: Jorn Janneck (Lund University, Sweden)
- DISPS-P3.1 Optimization of Flexible Filter Banks Based on Fast-Convolution
- DISPS-P3.2 Integer Word-length Optimization for Fixed-point Systems
- DISPS-P3.3 An energy-efficient VLSI architecture for pattern recognition via deep embedding of computation in SRAM
- DISPS-P3.4 A Robust Message Passing Based Stereo Matching Kernel via System-Level Error Resiliency
- DISPS-P3.5 Low power implementation of digital predistortion filter on a heterogeneous application specific multiprocessor
- DISPS-P3.6 A Reduced PAPR PR-NMDFB Based DUC Architecture for Transmit Downlink of Combined 3GPP LTE and UMTS Signals
- DISPS-P3.7 Adaptive Dual-Threshold Neural Signal Compression Suitable for Implantable Recording
- DISPS-P3.8 Low Peak-to-Average Ratio OFDM Chirp Waveform Diversity Design
- DISPS-P3.9 Simplified addressing scheme for mixed radix FFT algorithms
- DISPS-P3.10 Simulation-driven emulation of collaborative algorithms to assess their requirements for a large-scale WSN implementation
- DISPS-P3.11 Statistics Gathering Converters: System Level Metrics, Simulated Performance, and Process Variation Robustness
- DISPS-P3.12 Cluster-based Associative Memories Built From Unreliable Storage
- DISPS-P3.13 A Hybrid Approach to Offloading Mobile Image Classification
- DISPS-P3.14 Parallel programming of a symmetric Transport-Triggered Architecture with applications in flexible LDPC encoding