Speech, Language, and Graphical Models: Representation and Computation

Speech, Language, and Graphical Models: Representation and ComputationJeff A. Bilmes
Department of Electrical Engineering
University of Washington, SeattleAbstractGraphical models are a general statistical abstraction that can represent the inherent uncertainty within many scientific and engineering tasks. Recent research has indicated that they hold great promise for advancing speech and language processing. These time series, however, have properties that introduce unique and challenging research problems. The first part of this talk will present a variety of graph features and structures that solve many problems in speech and language. Two styles of structure determination are of particular interest: those whose goal is to represent knowledge, and those that are determined in a data-driven fashion specifically to reduce errors. Next, we will outline the computational challenges in applying this framework to speech and language, and describe our solutions. This includes dynamic graph triangulation methods, dynamic exact and approximate probabilistic inference methods, and a host of others, thereby making tractable computing with an enormous number of system variables.BiographyJeff A. Bilmes is an Assistant Professor in the Department of Electrical Engineering at the University of Washington, Seattle (and adjunct in Linguistics and also in Computer Science and Engineering). He co-founded the Signal, Speech, and Language Interpretation Laboratory at the University. He received a masters degree from MIT, and a Ph.D. in Computer Science at the University of California, Berkeley. Jeff is the author of the graphical models toolkit (GMTK), and has done much research on both structure learning of and fast probabilistic inference in dynamic Graphical models (DGMs). Jeff was a leader of the 2001 Johns Hopkins summer workshop team applying graphical models to speech and language, and has continued to lead in the speech/language community in this endeavor. His primary research lies in statistical graphical models, speech, language and time series processing, human-computer interaction, probabilistic machine learning, and high-performance computing. He was a general co-chair for IEEE Automatic Speech Recognition and Understanding 2003, and is a member of IEEE, ACM, and ACL. He is a 2001 CRA Digital-Government Research Fellow, and is a 2001 recipient of the NSF CAREER award. Additional information is available at: http://ssli.ee.washington.edu/~bilmesDate: April 29, 2005 (Friday)
Time: 2:00 pm
Location: EEB 248
Host: Shri Narayanan, EE-Systems (SIPI)
Contact: shri@sipi.usc.edu (x 06432)

Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248

Audiences: Everyone Is Invited

Contact: Regina Morton