Speech and Speaker Recognition: Recent Advances for In-Vehicle Speech Systems

John H. L. Hansen
University of Texas at Dallas

Monday, October 8, 2007 at 1:00PM

54-134 Engineering IV Building
Refreshments Served

Abstract: Speech and Speaker Recognition research has advanced significantly in recent years, but performance in real environments remains a major challenge. In this talk, we consider a number of recent research efforts in the field of robust speech recognition for hands-free in-vehicle route navigation systems. The system is comprised of a multi-microphone array processing front-end, environmental noise sniffer, robust feature and speech recognition system, and dialog manager and information servers. This research, supported by DARPA and NEDO (Japan) is contributing to international standards for driver behavior modeling to reduce distraction for information access. In this talk, we consider (i) array processing schemes and how they can be used to improve speech quality and speech recognition performance, and (ii) driver behavior modeling using CAN-bus vehicle signal data. For robust speech recognition, the concept of environmental sniffing is proposed to seek out knowledge in the acoustic environment, organize this knowledge, and provide decision information to potential speech tasks that will improve performance due to environmental variability. This is a sharp departure from the traditional ROVER paradigm, since we seek to formalize the solution during application of the speech system task. Our results show that an environmental sniffing front-end with a single speech recognizer can outperform a parallel ROVER paradigm for speech recognition in car environments. Finally, we discuss several additional applications for speaker recognition and stress classification for improved dialog systems for reduced cognitive loads.

Biography: John H.L. Hansen, (IEEE S'81-M'82-SM'93-F’07) received the Ph.D. and M.S. degrees in Electrical Engineering from Georgia Institute of Technology, Atlanta, Georgia, in 1988 and 1983, and B.S.E.E. degree from Rutgers University, College of Engineering, New Brunswick, N.J. in 1982. He joined University of Texas at Dallas (UTD), Erik Jonsson School of Engineering and Computer Science in the fall of 2005, where he is Professor and Dept. Chairman of Electrical Engineering, and holds the Distinguished University Chair in Telecommunications Engineering. He also holds a joint appointment as Prof. in School of Brain and Behavioral Sciences (Speech & Hearing). At UTD, he established the Center for Robust Speech Systems (CRSS) which is part of the Human Language Technology Research Institute. Previously, he served as Dept. Chairman and Prof. in Dept. of Speech, Language and Hearing Science, and Prof. in Dept. of Electrical & Computer Engineering, Univ. of Colorado Boulder (1998-2005), where he co-founded the Center for Spoken Language Research. He is serving as Member of the IEEE Signal Processing Society Speech Technical Committee and IEEE Signal Processing Educational Technical Committee. He previously served as IEEE Signal Processing Society Distinguished Lecturer (2005/06), Technical Advisor to U.S. Delegate for NATO (IST/TG-01), Associate Editor for IEEE Trans. Speech & Audio Processing (1992-99), Associate Editor for IEEE Signal Processing Letters (1998-2000), Editorial Board Member for the IEEE Signal Processing Magazine (2001-03). He has also served as guest editor of the Oct. 1994 special issue on Robust Speech Recognition for IEEE Trans. Speech & Audio Proc. He is an IEEE Fellow, and has supervised 39 PhD/MS) thesis candidates, recipient of the 2005 University of Colorado Teacher Recognition Award, and author/co-author of 255 journal, conference papers, and 7 books in the field of speech processing and language technology, coauthor of the textbook Discrete-Time Processing of Speech Signals, (IEEE Press), and lead author of the report “The Impact of Speech Under ‘Stress’ on Military Speech Technology,” (NATO RTO-TR-10). He served as General Chair for Interspeech/ICSLP-2002: Inter. Conf. on Spoken Language Processing, Sept. 16-20, 2002, and will serve as Technical Program Chair for IEEE ICASSP-2010, Dallas, TX.