This lecture will present recent advances and central issues in multimedia signal processing, speech processing/recognition in particular, from the speaker’s personal industrial and academic perspectives. Multimedia technologies represent rich applications and interactions among a variety of information sources including speech, music/audio, graphics, animation, image, video, and text/language. They also span over wide-ranging information processing tasks including coding/compression, transmission/networking, analysis, synthesis, perception, recognition, understanding, and retrieval. Future multimedia technology development will require an increasing level of intelligence, for which modeling and learning are two central issues. As a concrete example, this lecture will focus on the development of speech recognition and understanding technology over the past four decades and elaborate on the key roles that modeling and learning have been playing in the technology development.
Li Deng was Professor at the University of Waterloo, Ontario, 1989–1999, and is currently Principal Researcher at Microsoft Research, Redmond. He has published over 300 refereed papers in leading international conferences and journals, 15 book chapters, and two books. He has over 20 patents as inventor or co-inventor in acoustics, speech/language technology, multimedia/multi-sensor human-computer interaction, and signal processing. He currently serves on the IEEE Signal Processing Society’s Multimedia Signal Processing Technical Committee and is Area Editor of IEEE Signal Processing Magazine. He was a Technical Chair of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP04), and the General Chair of the IEEE Workshop on Multimedia Signal Processing, 2006.
For more information, see http://www.icics.ubc.ca/news/images/dls2007.pdf
When:
Thursday, November 22, 2007 - 14:30 to 16:00
Where:
Dempster Room 310
Tags: