Other Related Papers
Title |
Author(s) |
Published in |
Download |
Comments |
| A Query-by-Singing System based on Dynamic Programming | J. S. R. Jang M. Y. Gao |
International Workshop on Intelligent Systems Resolutions (the 8th Bellman Continuum) | [PDF] | |
| Content-based Music Retrieval Using Linear Scaling and Branch-and-bound Tree Search | J. S. R. Jang H. R. Lee M. Y. Kao |
ICME 2001 | [PDF] | |
| A Top-down Approach to Melody Match in Pitch Contour for Query by Humming | X. Wu M. Li J. Liu J. Yang Y. Yan |
ISCSLP 2006 | [PDF] | |
| Query by humming of midi and audio using locality sensitive hashing | M. Ryynanen A. Klapuri |
ICASSP 2008 | [PDF] |
Title |
Author(s) |
Published in |
Download |
Comments |
| A simple and efficient method to align very long speech signals to acoustically imperfect transcriptions | G. Bordel S. Nieto M. Penagarikano L. J. Rodriguez-Fuentes A. Varona |
Interspeech 2012 | [PDF] | |
| Automatic Phoneme Segmentation Using Auditory Attention Features | O. Kalinli | Interspeech 2012 | [PDF] | |
| Automatic Speech Segmentation Using Probabilistic Latent Component | S. Ghosh T.V. Sreenivas |
Interspeech 2012 | [PDF] | |
| Sentence Detection Using Multiple Annotations | A. Lee J. Glass |
Interspeech 2012 | [PDF] | MIT的, 使用三大類的features來做 |
| Toward an Optimum Feature Set and HMM Model Parameters for Automatic Phonetic Alignment of Spontaneous Speech | M. Karnjanadecha S. A. Zahorian |
Interspeech 2012 | [PDF] | |
| Word Prominence Detection using Robust yet Simple Prosodic Features | T. Mishra V. K. R. Sridhar A. Conkie |
Interspeech 2012 | [PDF] |
Title |
Author(s) |
Published in |
Download |
Comments |
| Joint-Sequence Models for Grapheme-to-Phoneme Conversion | M. Bisani H. Ney |
Speech Communication 2008 | [PDF] | Tool download/installation readme here |
Title |
Author(s) |
Published in |
Download |
Comments |
| A Study on Speaker Adaptation of Continuous Density HMM Parameters | Chin-Hui Lee Chih-Heng Lin Biing-Hwang Juang |
ICASSP 1990 | [PDF] [PPT] |
MAP 經典 paper |
| Speaker Adaptation of HMMs Using Linear Regression | C.J. Leggetter P.C. WoodLand |
CUED/F-INFENG/TR. 181, June 1994 | [PDF] [PPT-1] [PPT-2] |
|
| Speaker Adaptation using Constrained Estimation of Gaussian Mixtures | V. V. Digalakis D. Rtischev L. G. Neumeyer |
IEEE Transactions on Speech and Audio Processing, 3:357-366, 1995 | [PDF] | |
| Flexible Speaker Adaptation using Maximum Likelihood Linear Regression | C.J. Leggetter P.C. WoodLand |
Proc. ARPA Spoken Language Technology Workshop, p104~109, 1995 | [PDF] [PPT] |
看完這篇就差不多知道 MLLR 在做啥, 也可以了解 speaker adaptation 在做啥, 但數學細節很多... |
| Structural MAP Speaker Adaptation Using Hierarchical Priors | Koichi Shinoda Chin-Hui Lee |
ASRU 1997 Proceedings | [PDF] [PPT] |
|
| Structural Maximum A Posteriori Linear Regression for Fast HMM Adaptation | Olivier Siohan Tor Andre Myrvoll Chin-Hui Lee |
Computer Speech & Language 2002 | [PDF] [PPT] |
Title |
Author(s) |
Published in |
Download |
Comments |
| Minimum Phone Error and I-Smoothing for Improved Discriminative Training | D. Povey P. C. Woodland |
ICASSP 2002 | [PDF] | |
| Discriminative Training for Large Vocabulary Speech Recognition | Daniel Povey | Ph.D Dissertation, University of Cambridge, July 2004 | [PDF] | MPE 的原版博士論文, 很長一篇 |
| 最小化音素錯誤鑑別式聲學模型學習於中文大詞彙連續語音辨識之初步研究 An Initial Study on Minimum Phone Error Discriminative Learning of Acoustic Models for Mandarin Large Vocabulary Continuous Speech Recognition |
郭人瑋 | Master Thesis, NTNU, June 2005 | [PDF] |
也是一篇有關 MPE 的精釆論文, follow Dan Povey 那篇做下來的, 雖然是一篇碩士論文, 但請用看博士論文的心態去看這篇 @@ |
| 資料選取方法於鑑別式聲學模型訓練之研究 Training Data Selection for Discriminative Training of Acoustic Models |
朱芳輝 | Master Thesis, NTNU, February 2008 | [PDF] | follow 郭人瑋那篇做下來的 |
Title |
Author(s) |
Published in |
Download |
Comments |
| Maximum Mutual Information Estimation of Hidden Markov Model Parameters for Speech Recognition | L. R. Bahl P. F. Brown P. V. de Souza R. L. Mercer |
ICASSP 1986 | [PDF] | MMI 的經典 paper, 但我沒看過, 不知道可以幹麻 =.= |
| Speaker-Independent Phone Recognition Using Hidden Markov Models | K. F. Lee H. W. Hon |
TASSP (IEEE Trans. on Acoustics, Speech, and Signal Processing) 1989 | [PDF] | 經典 paper, 用 HMM 來做語音辨識的始祖 paper, 必讀 |
| A Tutorial on Hidden Markov Models and Selected Aplications in Speech Recognition | L. R. Rabiner | Proceedings of the IEEE, 1989 | [PDF] | 經典HMM tutorial, 必讀 |
| A Tutorial on Support Vector Machines for Pattern Recognition | C. J. C. Burges | Data Mining and Knowledge Discovery, 1998 | [PDF] | 網路上找到的 SVM tutorial |
| Automatic Construction of Regression Class Tree for MLLR via Model-based Hierarchical Clustering | Shih-Sian Cheng Yeong-Yuh Xu Hsin-Min Wang Hsin-Chia Fu |
TASLP, 2006 - Springer | [PDF] | 利用 BIC 加上 top-down, bottom-up approach 來自動建立MLLR所用的二元樹 |
| Linear Discriminant Feature Extraction for Speech Recognition | 李鴻欣, 臺灣師範大學 | NeGSST 2008 暑期講習會 | [PPT] [MP3] |
An excellent presentation on LDA (Linear Discriminant Analysis), some remarks and comparative studies, and variations of LDA. |
| A Brief Maximum Entropy Tutorial | A. Berger | Online Tutorial, 1996 | [PPT] |