
CIAIR
|
Special
Workshop in MAUI (SWIM)
Lectures by Masters in Speech Processing
Maui, Hawaii
January
12-14, 2004
|
 |
The Complete
Technical Program will be held at the Prince Ball Room of the
Maui Prince Hotel and Resort.
Technical
Session 4 (Tuesday, January 13, 13:30-15:30 --- Oral
Summaries: 13:45 - 14:00)
Decoder and Strategies
Chair: Alejandro Acero
|
|
Paper
ID
|
Presentation
Order
|
Title
|
Authors
|
Affiliation
|
|
205
|
4.1
|
Spoken
language Processing using Weighted Finite State Transducers |
Isabel
Trancoso |
INESC
ID, Lisboa, Portugal |
| Diamantino
Caseiro |
INESC
ID, Lisboa, Portugal |
|
258
|
4.2
|
A
Hybrid HMM/Baysian Network approach to robust speech recognition |
Satoshi
Nakamura |
ATR,
Japan |
| Konstantin
Markov |
ATR,
Japan |
|
262
|
4.3
|
Generalized
Word Posterior Probability for Minimum Word Error Rate Speech
Recognition |
Frank
Soong |
ATR,
Japan |
| Wai-Kit
Lo |
ATR,
Japan |
|
211
|
4.4
|
A
Semantically Structured Language Model |
Alejandro
Acero |
Microsoft,
USA |
| Ye-Yi
Wang |
Microsoft,
USA |
| Kuansan
Wang |
Microsoft,
USA |
|
213
|
4.5
|
MAXIMUM
ENTROPY DIRECT MODELS FOR SPEECH RECOGNITION |
Yuqing
Gao |
IBM
T. J. Watson Research Center, New York, USA |
| Jeff
H.-K. Kuo |
IBM
T. J. Watson Research Center, New York, USA |
|
218
|
4.6
|
Scaling
Up: Learning Large-Scale Recognition Methods from Small-Scale
Recognition Teasks |
Nelson
Morgan |
ICSI,
Berkeley, USA |
| Barry
Chen |
ICSI,
Berkeley, USA |
| Qifeng
Zhu |
ICSI,
Berkeley, USA |
| Andreas
Stolcke |
ICSI,
Berkeley, USA |
|
215
|
4.7
|
Modeling
human interaction in meetings based on audio and video information |
Herv'e
Bourlard |
IDIAP,
Switzerand |
| Iain
McCowan |
IDIAP,
Switzerand |
| Daniel
Gatica-Perez |
IDIAP,
Switzerand |
| Samy
Bengio |
IDIAP,
Switzerand |
| Darren
Moore |
IDIAP,
Switzerand |
|
216
|
4.8
|
Some
Emerging Concepts in Speech Recognition |
Hynek
Hermansky |
IDIAP,
Switzerand |
| Herv'e
Bourlard |
IDIAP,
Switzeran |
|
224
|
4.9
|
Framework
for Systematization and Application of Large-scale Knowledge
Resources |
Sadaoki
Furui |
Tokyo
Insitute of Technology, Tokyo, Japan |
|
226
|
4.10
|
A
Collaborative Approach Towards Next Generation ASR |
Chin-Hui
Lee |
Georgia
Institute of Technology |
| Biing-Hwang
"Fred" Juang |
Georgia
Institute of Technology |
|
Last Update:
Monday, September 21, 2003 11:52:30 AM
|