|
Technical Program
This is the final program as it actually happened on the day. You can look at all the papers in a single PDF file, or you can click on the talk titles below to view the corresponding paper.
0845-0900 | Welcome and introduction |
Morning Session: Perception and Music |
0900-0930 |
A Probability Model for Interaural Phase Difference (pp.1-6)
Michael Mandel, Columbia University; Daniel Ellis, Columbia University
|
0930-1000 |
Sparseness and speech perception in noise (pp.7-12)
Guoping Li, Institute of Sound and Vibration Research, University of
Southampton; Mark E. Lutman, Institute of Sound and Vibration Research,
University of Southampton
|
1000-1030 | Break/refreshments |
1030-1100 |
Frequency Component Restoration for Music Sounds Using Local Probabilistic Models with Maximum Entropy Learning (pp.12-17)
Tomonori Izumitani, NTT Communication Science Laboratories; K. Kashino,
NTT Communication Science Laboratories
|
1100-1130 |
A statistical model of timbre perception (pp.18-23)
Hiroko Terasawa, Stanford University ; Malcolm Slaney, Yahoo! Research ;
Jonathan Berger, Stanford University
|
Midday Session: Source Separation |
1130-1200 |
The Iroquois Model: Using Temporal Dynamics to Separate Speakers (pp.24-30)
Steven Rennie, IBM; Peder Olsen, IBM; John Hershey, IBM;
Trausti Kristjansson, IBM
|
1200-1230 |
Estimating Single-Channel Source Separation Masks: Relevance Vector Machine Classifiers vs. Pitch-Based Masking (pp.31-36)
Ron J. Weiss, Columbia University; Daniel P. W. Ellis, Columbia University
|
1230-1400 |
Lunch |
1400-1430 |
Structuring Time Domain Blind Source Separation Algorithms for CASA Integration (pp.37-41)
Bjoern Schoelling, Martin Heckmann, Honda Research Institute Europe
GmbH; Frank Joublin, Honda Research Institute Europe GmbH; Christian
Goerick, Honda Research Institute Europe GmbH
|
1430-1500 |
Leak Energy Based Missing Feature Mask Generation Its Evaluation with Simultaneous Speech Recognition (pp.42-47)
Shun'ichi Yamamoto, Kyoto University; Kazuhiro Nakadai, Honda Research
Institute Japan Co., Ltd.; Mikio Nakano, Honda Research Institute Japan
Co., Ltd.; Hiroshi Tsujino, Honda Research Institute Japan Co., Ltd.;
Ryu Takeda, Kyoto University; Kazunori Komatani, Kyoto University;
Tetsuya Ogata, Kyoto University; Hiroshi G. Okuno, Kyoto University
|
Keynote |
1500-1530 | Keynote: Towards microscopic models of speech perception
Martin Cooke, Sheffield University
|
1530-1600 |
Tea break |
Afternoon Session Speech Analysis, Recognition, and Synthesis |
1600-1630 |
Improving the Noise-Robustness of Mel-frequency Cepstral Coefficients for Speech Processing (pp.48-52)
Sourabh Ravindran, David V. Anderson, Georgia Tech; Malcolm Slaney,
Yahoo! Research
|
1630-1700 |
Speech Recognition for a Robot under its Motor Noises by Selective Application of Missing Feature Theory and MLLR (pp.53-58)
Yoshitaka Nishimura, University of Tokyo; Mikio Nakano, Honda Research
Institute Japan Co., Ltd.; Kazuhiro Nakadai, Honda Research Institute
Japan Co., Ltd.; Hiroshi Tujino, Honda Research Institute Japan Co.,
Ltd.; Mitsuru Ishizuka, University of Tokyo
|
1700-1730 |
LSM-Based Feature Extraction for Concatenative Speech Synthesis (pp.59-64)
Jerome Bellegarda, Apple Computer
|
1730-1800 |
Study of Noise Robust Voice Activity Detection Based on Periodic Component to Aperiodic Component Ratio (pp.65-70)
Kentaro Ishizuka, Tomohiro Nakatani, NTT Communication Science Laboratories
|
Dan Ellis
<dpwe@ee.columbia.edu>
Last updated: Fri Sep 22 09:50:14 AM EDT 2006
|