Sackler Colloquia banner

Human-Machine Communication by Voice

Organized by Lawrence Rabiner

February 8-9, 1993
Irvine, CA

Meeting Overview:
The fields of synthesis and speech recognition have matured to the point where a wide range of applications is now within sight and may well become practical within a few years. Because of the impact of speech synthesis and recognition on science and technology, it is important to fully understand both the strengths and limitations of our current understanding in these two key areas of research. It is also important to understand the direction in which the research is heading to see what future applications will emerge as synthetic speech quality becomes more natural and as restrictions on vocabulary size, user population and syntactical constraints become more relaxed in speech recognition.

February 8
Jack Halpern, Chairman, NAS Committee on Scientific Programs, Welcome Address
Lawrence Rabiner. AT&T Bell Laboratories, Colloquium Chair, Charge to the Conference

Session One - Scientific Bases of Human-Machine Communication by Voice

The Role of Voice in Human-Machine Communication
Philip R. Cohen, SRI International

Overview of Speech Communication
James L. Flanagan, CAIP Center, Rutgers University

Ronald W. Schafer, Georgia Institute of Technology, Discussion Leader

Session Two - Speech Synthesis Today

Models of Speech Synthesis
Rolf Carlson, Royal Institute of Technology (KTH)

Linguistic Aspects of Speech Synthesis
Johnathan Allen, Massachusetts Institute of Technology

Mark Liberman, University of Pennsylvania, Discussion Leader

Session Three - Speech Recognition Technology

Overview of Speech Recognition Technology
John Makhoul, BBN Systems and Technologies

Training and Search Methods
Fredrick Jelinek, IBM Watson Research Center

Stephen E. Levinson, AT&T Bell Laboratories, Discussion Leader

Session Four - Natural Language Understanding Technology

Models of Natural Language Understanding
Madeleine Bates, BBN Systems and Technologies

Integration of Speech with Natural Language Understanding
Robert C. Moore, SRI International

Lynette Hirschman, Massachusetts Institute of Technology, Discussion Leader

Social Hour and Dinner

Lawrence Rabiner, Introduction of After-Dinner Speaker

After Dinner Speaker: Yasuo Kato, NEC Corporation, The Future of Voice Processing Technology in the World of Computers and Communication

February 9

Session Five - Applications of Voice Processing Technology I

Laboratories Applications of Voice Processing Technology in Telecommunications
Jay G. Wilpon, AT&T Bell

Aids for Handicapped People: Assistive Technology for Voice Communication
Harry Levitt, City University of New York Graduate School

Chris Seelbach, Seelbach Associates, Discussion Leader

Session Six - Applications of Voice Processing Technology II

Military/Government Applications of Speech Processing Technology
Clifford J. Weinstein, MIT Lincoln Laboratory

General/Consumer Applications of Voice Processing
George Doddington, SRI International (Currently at SISTO/DARPA)

John Oberteuffer, ASR News, Discussion Leader

Session Seven - Technology Deployment

What Does Voice Processing Technology Support Today
Ryohei Nakatsu, NTT Basic Research Laboratories

Research User Interfaces for Voice Applications
Candace Kamm, Bell Communications

David Roe, AT&T Bell Laboratories, Discussion Leader

Session Eight - Technology in 2001

New Research Directions
Bishnu S. Atal, AT&T Bell Laboratories

Towards the Ultimate Synthesis/Recognition System
Sadaoki Furui, NTT Human Interface Laboratories

New Trends in Natural Language Processing
Mitchell Marcus, University of Pennsylvania

Title TBA
Frank Fallside, University of Cambridge

Powered by Convio
nonprofit software