Topic: "Automatic Speaker Authentication"

Date: Monday, 23 October 2000

Time: 4:00pm - 5:00pm

Venue: Lecture Theatre F
			   Academic Concourse (near lift nos. 25/26)
			   HKUST

			   ABSTRACT

			   Following a brief introduction of Multimedia Communications Research
			   Laboratory in Bell Labs, Lucent Technologies, I will review the
			   state-of-the-art technologies in automatic speaker authentication.
			   Traditional speaker authentication focuses on speaker verification (SV)
			   and speaker identification, which is accomplished by matching the
			   speaker's voice with his or her registered speech patterns. In our resent
			   research, we propose a new technique called Verbal Information
			   Verification (VIV), in which spoken utterances of a claimed speaker are
			   verified against the key (usually confidential) information in the
			   speaker's registered profile automatically to decide whether the claimed
			   identity should be accepted or rejected. Using the proposed sequential
			   test procedure involving human-machine dialogs, we achieved an error-free
			   result in a telephone speaker authentication experiment with 100 speakers.
			   I will also introduce the public evaluation in this area and present some
			   results.

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

				Qi (Peter) Li received the Ph.D. degree in electrical engineering from
						University of Rhode Island, Kingston, USA. From 1988 to 1994, he worked at
						F.M. Engineering and Research, Norwood, MA, where he worked in research on
						pattern recognition algorithms and in real-time systems. In 1991, he
						attended Harvard University to study statistical theory and methods. In
						1995, he joined Bell Laboratories, Murray Hill, NJ, where he is currently
						a member of technical staff in the Dialogue Systems Research Department.
						His research interests include speaker and speech recognition, robust
						features, fast search algorithms, stochastic modeling, fast discriminative
						learning, and neural networks. He has published regularly and holds
						patents in his research areas.

						Dr. Li has been active as a reviewer for several journals, including IEEE
						Transactions on Speech and Audio Processing, and as a Local Chair for the
						IEEE 1999 Workshop on Automatic Identification. He has received two awards
						and is listed in Who's Who in America, Millennium Edition.