ICASSP '98 Main Page

General Information

Conference Schedule

Technical Program

    Overview
    50th Annivary Events
    Plenary Sessions
    Special Sessions
    Tutorials
    Technical Sessions

Invited Speakers

Registration

Exhibits

Social Events

Coming to Seattle

Satellite Events

Call for Papers/
Author's Kit

Future Conferences

Help

Technical Session - SP9

Session SP9:	Speech Synthesis and Voice Conversion (Lecture)
Time and Place:	Wednesday, May 13, 1:00 pm - 3:00 pm, Room 605/606
Chair:	E. Moulines (ENST, France)

1:00 pm	SP9.1 TD-PSOLA versus Harmonic Plus Noise Model in Diphone Based Speech Synthesis A. Syrdal, Y. Stylianou, L. Garrison, A. Conkie, J. Schroeter (AT&T Labs, USA); [abstract] [manuscript]
1:15 pm	SP9.2 A Hybrid Approach to Synthesize High Quality Cantonese Speech M. Chu, P. Ching (Chinese University of Hong Kong, P R China); [abstract] [manuscript]
1:30 pm	SP9.3 A System for Voice Conversion Based on Probabilistic Classification and a Harmonic Plus Noise Model Y. Stylianou (AT&T Labs - Research, USA); O. Cappé (ENST, France); [abstract] [manuscript]
1:45 pm	SP9.4 Spectral Voice Conversion for Text-to-Speech Synthesis A. Kain, M. Macon (Oregon Graduate Institute, USA); [abstract] [manuscript]
2:00 pm	SP9.5 Speaker Transformation using Sentence HMM Based Alignments and Detailed Prosody Modification L. Arslan, D. Talkin (Entropic Research Lab, USA); [abstract] [manuscript]
2:15 pm	SP9.6 Automatic Generation of Synthesis Units for Trainable Text-to-Speech Systems H. Hon, A. Acero, X. Huang, J. Liu, M. Plumpe (Microsoft Research, USA); [abstract] [manuscript]
2:30 pm	SP9.7 Optimizing a Neural Net for Speaker and Task Dependent Pitch Contour Generation H. Ralf, H. Martin (Siemens AG, Germany); [abstract] [manuscript]
2:45 pm	SP9.8 Practical High-Quality Speech and Voice Synthesis Using Fixed Frame Rate ABS/OLA Sinusoidal Modeling E. George (Texas Instruments, USA); [abstract] [manuscript]