| Sun, Dec 14, 1997 | |
| 18:00-19:30 | Dinner |
| 19:30-19:40 | Welcome |
| 19:40-20:30 | Keynote Speaker: Professor Jim Flanagan, Rutgers Univ. Synergistic Modalities for Human/Machine Communication |
| 20:30-21:20 | Keynote Speaker: Professor David Donoho, Stanford Univ. Evolution and Optimal Representation |
Mon, Dec 15, 1997 |
| 7:00-9:00 | Breakfast |
| 9:00-12:30 | Session 1: Dialogue Systems
and Voice Agent Technologies Organizers: Jay Wilpon, Richard Schwartz |
| 9:00-9:30 | Invited Speaker: Candace Kamm, AT&T Labs - Research Design and Evaluation of Spoken Dialog Systems |
| 9:30-10:00 | Invited Speaker: Marie Meteer, BBN Collaborative Systems |
| 10:00-10:30 | Poster Introduction |
| 10:30-11:30 | Break and Poster |
| 11:30-12:30 | Discussion |
| 12:30-14:00 | Lunch |
| 14:00-17:40 | Session 2: Mathematical
Foundations and New Paradigms of SRU Organizers: Chin Lee, Joe Picone |
| 14:00-14:30 | Invited Speaker: Li Deng A Dynamic, Feature-Based Approach to Speech Modeling and Recognition |
| 14:30-15:00 | Invited Speaker: Martin Russel Progress Towards Speech Models that Model Speech |
| 15:00-15:40 | Poster Introduction |
| 15:40-16:40 | Break and Poster |
| 16:40-17:40 | Discussion |
| 17:40-19:30 | Dinner |
| 19:30-21:30 | Session 3: Lessons Learned from
Human Speech Recognition System Organizers: Roger Moore, Mari Ostendorf |
| 19:30-20:00 | Invited Speaker: Louis Pols, Univ. of Amsterdam Flexible Human Speech Recognition |
| 20:00-20:30 | Invited Speaker: Anne Fernald, Stanford Univ. Emerging Understandings: Experimental Research on the Early Development of Speech Comprehension |
| 20:30-21:30 | Discussion | Tues, Dec 16, 1997 |
| 7:00-9:00 | Breakfast |
| 9:00-12:20 | Session 4: Efficient Decoding
Algorithms and Implementations Organizers: Volker Steinbiss, Ponani Gopalakrishnan |
| 9:00-9:30 | Invited Speaker: Hermann Ney Progress in Dynamic Programming Search for LVCSR |
| 9:30-10:00 | Invited Speaker: Fil Alleva Search Organization in the Whisper Continuous Speech Recognition System |
| 10:00-10:20 | Poster Introduction |
| 10:20-11:20 | Break and Poster |
| 11:20-12:20 | Discussion |
| 12:20-14:00 | Lunch |
| 14:00-17:40 | Session 5: Robust Modeling in
Acoustics, Lexicon and Language Organizers: Richard Stern, Kiyohiro Shikano, Jean-Claude Junqua |
| 14:00-14:30 | Invited Speaker: Chin Lee, Bell Labs Adaptive Compensation for Robust Speech Recognition |
| 14:30-15:00 | Invited Speaker: Richard Lippmann, MIT Robust Recognition with Time-Varying Filtering, Interruptions, and Noise |
| 15:00-15:40 | Poster Introduction |
| 15:40-16:40 | Break and Poster |
| 16:40-17:40 | Discussion |
| 17:40-19:30 | Dinner |
| 19:30-21:30 | General Discussion | Wed, Dec 17, 1997 |
| 7:00-9:00 | Breakfast |
| 9:00-12:30 | Session 6: Applications of Speech
Recognition and Understanding (SRU) Systems Organizers: Brian Hanson, Wu Chou |
| 9:00-9:30 | Invited Speaker: Lawrence R. Rabiner, AT&T Labs Applications of Speech Recognition in the Area of Telecommunications |
| 9:30-10:00 | Invited Speaker: David Thomson, Lucent Technologies Ten Case Studies of the Effect of Field Conditions on Speech Recognition Error |
| 10:00-10:30 | Poster Introduction |
| 10:30-11:30 | Break and Poster |
| 11:30-12:30 | Discussion |
| 12:30-13:30 | Lunch |
| 13:30-14:00 | Adjourn |
| 15:00-17:00 | Open House at STL/Panasonic Technologies |
The workshop committee invites you to the Open House at STL/Panasonic Technologies. This is a conference-related tour and is not formally part of the workshop program.