On July 21-23, 1997, UCLA Extension will present the short course,
"Automatic Speech Recognition: Fundamentals and Applications", on the
UCLA campus in Los Angeles.
The instructors are Abeer Alwan, PhD, Assistant Professor, Electrical
Engineering Department, UCLA, and Ananth Sankar, PhD, Senior Research
Engineer, SRI International.
Automatic Speech Recognition (ASR) has emerged as a promising area
for applications such as telephone voice dialing, database access,
human-computer interactions and hands-free applications such as car
phones. Since speech is the most direct form of human communication,
ASR can enhance the ease, speed, and effectiveness with which humans
can direct machines to accomplish desired tasks. Speech recognition
has become an established research area and current understanding has
already produced several fielded applications.
This course is intended to provide an understanding of the basic
concepts of speech recognition including speech signal processing and
feature extraction, and statistical pattern recognition and its
applications in speech recognition. The course also covers recent
developments in special problem areas such as the recognition of noisy
speech or accented speech. The instructors assume basic knowledge of
signal processing and statistical analysis, and the lectures are
designed to prepare participants for development work in speech
recognition. The course should also offer enough background in speech
recognition theory to foster the successful development of
applications, and to expose new solutions to specific problems in
The course fee is $1195, which includes extensive course materials.
These materials are for participants only, and are not for sale.
For additional information and a complete course description, please
contact Marcus Hennessy at:
(310) 206 -2815 fax
mhenness at unex.ucla.eduhttp://www.unex.ucla.edu/shortcourses/
This course may also be presented on-site at company locations.