Program Overview
Keynote Speeches [Dec 11 (Tue) 14:30-16:30]
- ·Prof.
Renato De Mori (Univ. Avignon, France)
- "Spoken Language Understanding:
A Survey"
- ·Prof.
Jun'ichi Tsujii (Univ. Tokyo, Japan / Univ. Manchester, UK / Former
President of ACL)
- "Combining Statistical Models with Symbolic Grammar in Parsing"
Regular Sessions
All papers will be presented in a poster format, except those by invited speakers. The poster board is 180cm (72inch) wide and 210cm (84inch) tall.
Each session consists of an invited talk (45min) and poster presentations (90min) followed by a panel discussion (45-60min). The poster must be placed on the board at the beginning of the session.
Each session consists of an invited talk (45min) and poster presentations (90min) followed by a panel discussion (45-60min). The poster must be placed on the board at the beginning of the session.
- S1: Acoustic Modeling and Robust ASR
-
- Invited talk: Li
Deng (Microsoft, USA)
- Poster Presentations
- Panel Discussion:
Hynek Hermansky +
Jeff Bilmes,
Jordan Cohen,
Ralf Schlueter,
Herve Bourlard,
Li Deng
- Invited talk: Li
Deng (Microsoft, USA)
- S2: Language Modeling and Speech Understanding
-
- Invited talk: Ye-yi
Wang (Microsoft, USA)
- Poster Presentations
- Panel Discussion:
Tatsuya Kawahara +
Giuseppe Riccardi,
Gary Geunbae Lee,
Michiel Bacchiani,
Ye-yi Wang
-
"Spoken Language Understanding for New-Generation Dialog
Systems"
- Invited talk: Ye-yi
Wang (Microsoft, USA)
- S3: Statistical Modeling and Learning
-
- Invited talk: Jeff
Bilmes (Univ. Washington, USA)
- Poster Presentations
- Panel Discussion:
Jeff Bilmes
, Tomoko Matsui +
Mark Gales,
Fred Juang,
Andrease Stolcke
-
"Towards better statistical modeling and learning for ASR
systems"
- Invited talk: Jeff
Bilmes (Univ. Washington, USA)
- S4: Speech Translation and LVCSR
-
- Invited talk: Stephan
Vogel (CMU, USA)
- Poster Presentations
- Panel Discussion:
Satoshi Nakamura +
Rohit Prasad,
Chiori Hori,
Evgeny Matusov,
George Saon,
Stephan Vogel
-
"Problems and future directions of speech translation technology"
- Invited talk: Stephan
Vogel (CMU, USA)
- S5: Spoken and Multi-modal Dialogue Systems
-
- Invited talk: Sharon
Oviatt (Incaa Designs, USA)
- Poster Presentations
- Panel Discussion:
Sharon Oviatt +
Kazuya Takeda,
John Hansen,
Brandon Roy,
Alex Acero
-
"Recording situated human communications"
- Invited talk: Sharon
Oviatt (Incaa Designs, USA)
- S6: Speech Mining and Information Retrieval
-
- Invited talk: Mark
Clements (Georgia Tech., USA)
- Poster Presentations
- Panel Discussion:
Timothy Hazen +
Lin-shan Lee,
Frank Seide,
Steve Renals,
Mark Clements
-
"Research Directions in Information Retrieval and Data Mining
of Spoken Audio Documents"
- Invited talk: Mark
Clements (Georgia Tech., USA)
Project Talks [Dec 10 (Mon) 18:00-20:00]
- ·Jordan Cohen (SRI, USA)
- "The GALE Project: A Description and an Update"
- ·Herve
Boulard (IDIAP, Switzerland)
- "Recognition and Understanding of Meetings: The AMI and AMIDA Projects"
- ·Sadaoki
Furui (Tokyo Tech, Japan)
- "Introduction of the METI Project "Development of Fundamental Speech Recognition Technology"
Banquet [Dec 11 (Tue) 16:45-20:00; Room: Aoi-den (4F east-side)]
The banquet will take place in the most gorgeous room in the hotel, Aoi-den, and be preceded by a cocktail party and then "traditional Japanese (Kyoto-style) performance", which you should not miss. Please come before dark to enjoy the scenic view and bring your camera.Demonstrations [Dec 12 (Wed) 18:00-20:00]
The demonstration session will be accompanied with some drink and food generously sponsored by Google.There are eleven demonstrations both from academia and industry.