[ Text | Word97 ]


fcclogo PUBLIC NOTICE

Federal Communications Commission
445 12th Street, S.W.
Washington, D.C. 20554
News media information 202 / 418-0500
Fax-On-Demand 202 / 418-2830
Internet: http://www.fcc.gov
ftp.fcc.gov



DA 01-1370
Released: June 6, 2001



GRAPHICAL MODELS FOR SPEECH RECOGNITION
AN OET TUTORIAL


The Office of Engineering and Technology will provide a tutorial on the use of graphical models (GMs) for speech recognition on Monday, June 11, from 10:30 a.m. to 12:00 p.m. at the Federal Communications Commission, 445 12th St. S.W., Room TW-C305, Washington, D.C. GMs are flexible statistical abstractions that offer promising new approaches to automatic speech recognition.

The presenter, Dr. Jeffrey A. Bilmes, is the 2001 Computing Research Association Digital Government Fellow. He is Associate Professor, Signal and Image Processing, at the University of Washington. Mr. Bilmes joined the University of Washington Department of Electrical Engineering faculty in the fall of 1999. He received a B.S. degree in Electrical Engineering and Computer Science from U.C. Berkeley in 1989, a S.M. degree from MIT in 1993, and a Ph.D. in Computer Science from U.C. Berkeley in 1999. He is the author of more than 40 journal and conference papers on topics ranging from speech and pattern recognition to parallel programming language design. His primary interests are in statistical modeling (particularly graphical approaches) and signal processing for pattern classification, speech recognition, language processing, and audio processing.

Members of the public may attend the presentation, and every effort will be made to accommodate as many people as possible. Admittance, however, will be limited to the seating available in the Commission meeting room. Please allow sufficient time for clearance through Commission security before the presentation begins. For additional information, contact Kent Nilsson at 202-418-0845 (e-mail: knilsson@fcc.gov).