-
Multimodal Analysis for Audio-Driven Human Body Animation
Mon, Sep 24, 2012 @ 11:00 AM - 12:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Engin Erzin, College of Engineering, Koç University, Istanbul, Turkey
Talk Title: Multimodal Analysis for Audio-Driven Human Body Animation
Abstract: This talk will present an overview of the recent multimedia signal processing research portfolio on audio-driven human body animation at the Multimedia, Vision and Graphics Laboratory (MVGL) of Koc University. The talk will focus on two key applications. The first one will be music-driven choreography synthesis, where a novel framework will be presented for learning many-to-many statistical mappings from musical measures to dance figures towards generating plausible music-driven dance choreographies. The second application will be on automatic synthesis of gesticulation in synchrony with speech, where the correlation between prosody, head and upper-body gestures will be in the focus.
Biography: Engin Erzin (Sâ88âMâ96âSMâ06) received the B.Sc., M.Sc., and Ph.D. degrees from the Bilkent University, Ankara, Turkey, in 1990, 1992, and 1995, respectively, all in electrical engineering. During 1995â1996, he was a postdoctoral fellow in the Signal Compression Laboratory, University of California, Santa Barbara. He joined Lucent Technologies in September 1996, and he was with the Consumer Products for one year as a Member of Technical Staff of the Global Wireless Products Group. From 1997 to 2001, he was with the Speech and Audio Technology Group of the Network Wireless Systems. He has been with the College of Engineering, Koç University, Sariyer-Istanbul, Turkey, as an assistant professor between January 2001 and July 2009 and as an associate professor since July 2009. Dr. Erzin is serving as an Associate Editor of the IEEE Transactions on Audio, Speech & Language Processing (2010-2013). His research interests include speech signal processing, audio-visual signal processing, human-computer interaction, and pattern recognition.
Host: Prof. Shrikanth Narayanan
Location: Ronald Tutor Hall of Engineering (RTH) - 320
Audiences: Everyone Is Invited
Contact: Mary Francis