Title:    Robust Speech Recognition and Adaptation   (Lecture)

Time: Wednesday, March 17, 3:45 PM - 5:45 PM

Location:    Tucson 5

Chair: Yifan Gong    (Texas Instruments)

3:45 PM    SP-14.1
Time-Varying Noise Compensation Using Multiple Kalman Filters
Nam Soo Kim (School of Electrical Engineering, Seoul National University)
[abstract]  [manuscript]

4:00 PM SP-14.2
A Segment-based C0 Adaptation Scheme for PMC-based Noisy Mandarin Speech Recognition
Wei-Tyng Hong, Sin-Horng Chen (Dep. of Communication Eng., National Chiao Tung University)
[abstract]  [manuscript]

4:15 PM SP-14.3
Improved Parallel Model Combination Techniques With Split Gaussian Mixtures For Speech Recognition Under Noisy Conditions
Jeih-weih Hung (Dept of Electrical Engineering, National Taiwan University), Jia-lin Shen (Institute of Information Science, Academia Sinica), Lin-shan Lee (Dept of Electrical Engineering, National Taiwan University)
[abstract]  [manuscript]

4:30 PM SP-14.4
Speech Recognition and Enhancement by A Nonstationary AR HMM with Gain Adaptation under Unknown Noise
Ki Yong Lee (School of Electronic Engineering, Soongsil University, 1-1 Sangdo-5Dong, Dongjak-Ku, Seoul, 156-743 Korea), Joohun Lee (Dept. of Information and Telecommunication, Dong-Ah College, Ansung, Korea), Gunther Ruske (Inst. for Human-Machine-Communication, Munich University of Technology, Germany)
[abstract]  [manuscript]

4:45 PM SP-14.5
Database and Online Adaptation for improved Speech Recognition in Car Environments
Alexander Fischer (Philips Research Laboratories, Aachen, Germany), Volker Stahl (Philips Research Laboratories Aachen, Germany)
[abstract]  [manuscript]

5:00 PM SP-14.6
Training of HMM with Filtered Speech Material for Hands-free Recognition
Diego Giuliani, Marco Matassoni, Maurizio Omologo, Piergiorgio Svaizer (ITC-IRST Centro per la Ricerca Scientifica e Tecnologica)
[abstract]  [manuscript]

5:15 PM SP-14.7
Incremental Enrollment of Speech Recognizers
Chafic E Mokbel (France Telecom - CNET - DIH/DIPS (Currently at IDIAP)), Olivier Collin (France Telecom - CNET - DIH/DIPS)
[abstract]  [manuscript]

5:30 PM SP-14.8
AUTOMATIC SPEECH RECOGNITION: A COMMUNICATION PERSPECTIVE
Bishnu S Atal (AT&T Labs, Florham Park, NJ 07932, USA)
[abstract]  [manuscript]

< SP-13 SP-15 >

Last Update: February 4, 1999 Ingo Höntsch