Learning the Design of VoIP Systems With High Perceptual Quality

时间：2010年7月9日（周五）下午14：00-15：00

地点：计算所 四层报告厅

报告人：Benjamin W. Wah, Chinese University of Hong Kong

摘要：In this talk, we present the design of real-time VoIP systems that can achieve high perceptual quality to their users. It focuses on the fundamental understanding of multiple objective quality metrics and their relationship to the play-out control strategy that affects the quality perceived by subjects in real time. By controlling the mouth-to-ear delay (MED) between the two clients, trade-offs can be made between the quality of the speech signals received and the interactivity of a conversation. Although there are many objective metrics for assessing the quality of a VoIP conversation, the evaluation of conversational quality is a largely unexplored area, and there is no single objective metric whose results match well with subjective results. To address this issue, our approach consists of a) designing an adaptive strategy using Bayesian analysis to schedule a small number of off-line subjective comparative tests, b) learning the mapping by a support vector machine between objective measures of network and conversational conditions at run time with respect to the MED that leads to the best subjective quality, and c) generalizing the mapping found to unseen network and conversational conditions. By demonstrating the success of the approach using network traces collected in PlanetLab and interactive conversations, our VoIP system can dynamically adapt to unseen conditions and can achieve high perceptual quality.

报告人简介：Benjamin W. Wah is currently the Provost of the Chinese University of Hong Kong. Before then, he served as the Director of the Advanced Digital Sciences Center in Singapore, as well as the Franklin W. Woeltge Endowed Professor of Electrical and Computer Engineering and Professor of the Coordinated Science Laboratory of the University of Illinois at Urbana-Champaign, Urbana, IL. He received his Ph.D. degree in computer science from the University of California, Berkeley, CA, in 1979. He had served on the faculty of Purdue University. He has received a number of awards for his research contributions, which include the IEEE CS Technical Achievement Award (1998), the IEEE Millennium Medal (2000), the Society for Design and Process Science Raymond T. Yeh Lifetime Achievement Award (2003), the IEEE CS W. Wallace-McDowell Award (2006), the Pan Wen-Yuan Outstanding Research Award (2006),the IEEE CS Richard E. Merwin Award (2007), the IEEE-CS Technical Committee on Distributed Processing Outstanding Achievement Award (2007), and the IEEE-CS Tsutomu Kanai Award (2009). Wah's current research interests are in the areas of nonlinear search and optimization, multimedia signal processing, and computer networks. He is a Fellow of the AAAS, ACM, and IEEE.