Research Topics in Automatic Speech Recognition

Speaker:	Dr. Brian MAK
		Associate Professor
		Department of Computer Science and Engineering
		The Hong Kong University of Science and Technology

Title:		"Research Topics in Automatic Speech Recognition"

Date:		Monday, 30 April 2007

Time:		4:00pm - 5:00pm

Venue:		Lecture Theatre F
		(Leung Yat Sing Lecture Theatre, near lift nos. 25/26)
		HKUST

Abstract:

The goal of automatic speech recognition (ASR) is to transcribe human
speech to text. The technology has been advancing by leaps and bounds in
the last 20 years, and commercial applications are getting into the
market. Nevertheless, it is still an emergent technology, and many
problems are still unsolved.

In this talk, I will first give you an introduction to ASR, with an
emphasis on its multi-disciplinary nature. Then, we will discuss some
interesting research problems of ASR.


*******************
Biography:

Dr. Brian Mak received the B. Sc. degree in Electrical Engineering from
the University of Hong Kong, the M.S. degree in Computer Science from the
University of California, Santa Barbara, USA, and the Ph.D. degree in
Computer Science from Oregon Graduate Institute of Science and Technology,
Portland, Oregon, USA. From 1990 until 1992, he was a research programmer
at the Speech Technology Laboratory of Panasonic Technologies Inc. in
Santa Barbara and worked on endpoint detection research in noisy
environment. From 1997 until his Ph.D. graduation in 1998, he was also a
research consultant at the AT&T Labs -- Research, Florham Park, New
Jersey, USA. Since April 1998, he has been with the Department of Computer
Science in the Hong Kong University of Science and Technology, and is now
an Associate Professor. He had been a visiting researcher to the
Department of Dialogue Systems Research, Multimedia Communications
Research Laboratory, Bell Laboratories, Murray Hill, New Jersey in Summer
2001, and to the Department 1, Spoken Language Translation Research
Laboratories, Advanced Telecommunication Research Institute ---
International in Spring 2003. He is currently a member of the IEEE Signal
Processing Society's Speech and Language Technical Committee, an associate
editor of the IEEE Signal Processing Letters, and serves on the editorial
board of Speech Communication.

His interests include acoustic modeling, speech recognition, spoken
language understanding, computer-assisted language learning, and machine
learning.