From: Kendra Smith
Sent: Wednesday, April 19, 2000 1:20 AM
To: M?crosöft Research Tech Talk, Sem. Notice
Cc: Kendra Smith
Subject: UW-Speech Processing Seminar: Wed, April 19th
UW-Speech Processing Seminar: Wed, April 19th
Speech Processing Seminar
http://rcs.ee.washington.edu/ssli/ssli-sem.html
University of Washington, Department of EE
Wednesday, 19 April 2000, 10:30-11:30
RM 203 EE/CS Bldg
Integrating Knowledge-Based and Data-Driven Techniques in
Acoustic Modeling for Speech Recognition
Katrin Kirchhoff
University of Washington
Although speech recognition research has made significant progress in
recent years, the overall performance of speech recognizers still does
not attain the level of human speech perception. In particular,
performance frequently deteriorates in adverse acoustic conditions
such as noise or room reverberation. To overcome these problems speech
researchers have looked at enriching the statistical modeling
techniques commonly used in speech recognition with expert knowledge
about speech production or perception. This talk will focus on the use
of knowledge about speech production, i.e. the articulatory processes
by which the acoustic speech signal is generated.
The first part of the talk will review the potential benefits of
articulatory representations in speech recognition. Part two will
describe several experiments involving (pseudo)articulatory-based
recognition components, which demonstrate the fact that articulatory
representations provide information which is complementary to that of
standard acoustic speech representations, and which can be
successfully integrated to reduce word error rate. The final part of
the talk will address the problem of acoustic-articulatory inversion
and describe preliminary work on data-driven identification of
acoustic cues for articulatory distinctions by rule extraction from
trained neural networks.