Making Machines Speak and Listen - Why It is Still Interesting

Date: Wednesday, March 23, 08:00 - 09:00
Location: Exhibit Hall C

Presented by

Prof. Biing Hwang (Fred) Juang, Georgia Institute of Technology

Abstract

Designing a machine that mimics human behavior, particularly the capability of speaking naturally and responding properly to spoken language, has intrigued engineers and scientists for centuries. The first workable engineering concept was the framework for the analysis and synthesis of speech proposed by Homer Dudley at Bell Telephone Laboratories in the 1930's. Since then, technological development in speech recognition and synthesis has made a remarkable progress, from a simple machine that responds to a small set of sounds of a phonemic nature to a sophisticated system that converses with human in fluently spoken natural language, in a limited and controlled sense. The progress, to a large extent, can be attributed to the data-driven approach supported by the underlying signal processing ideas and mathematical formalisms. Today, automatic speech systems find widespread application in tasks that require a human-machine interface, such as automatic call processing in the telephone network and query-based information systems that offer updated travel information, stock price quotations, weather reports, etc.

In light of these "successes," one might ask a rather penetrating question: Is speech processing, recognition as well as synthesis, a solved problem? In this talk, we’ll review some major highlights in the research and development of automatic speech systems in the past and attempt to answer the above question by pointing out the limitations of today’s speech technology and the remaining challenges. We’ll also discuss several new, exciting efforts that are interesting and inspiring, something that hold the potential of opening the next chapter of speech technology in this relentless scientific pursuit.

Speaker Biography

Professor Biing Hwang (Fred) Juang received his Ph.D. from University of California, Santa Barbara. He had worked at Speech Communications Research Laboratory (SCRL) and Signal Technology, Inc. (STI) on a number of Government-sponsored research projects. Notable accomplishments during the period include development of vector quantization for voice applications, voice coders at extremely low bit rates, 800 bps and around 300 bps, and robust vocoders for use in satellite communications. He was also a co-Principal Investigator for the project on co-channel separation of speech signals sponsored by the Department of Defense. Prof. Juang subsequently joined the Acoustics Research Department of Bell Laboratories in 1982, working in the area of speech enhancement, coding and recognition. Prof. Juang became Head/Director of Acoustics and Speech Research at Bell Labs, and Director of Multimedia Technologies Research at Avaya Labs (a spin-off of Bell Labs) in 2001. His group continued the long heritage of Bell Labs in speech communication research.

Prof. Juang has published extensively, including the book "Fundamentals of Speech Recognition," co-authored with L.R. Rabiner, "Pattern Recognition in Speech and Language Processing," with Wu Chou, and holds about twenty patents. He has served as Editor-in-Chief for the IEEE Transactions on Speech and Audio Processing, and a number of positions in the IEEE Signal Processing Society, including current Chair of its Fellow Evaluation Committee. Prof. Juang has received a number of technical awards, notable among which are several Best Paper awards in the area of speech communications and processing, the Technical Achievement Award from the IEEE Signal Processing Society, and the IEEE Third Millennium Medal. He is a Fellow of the IEEE, a Fellow of Bell Laboratories, and a member of the National Academy of Engineering of the United States. He is currently Motorola Foundation Chair Professor at the School of Electrical & Computer Engineering, Georgia Institute of Technology which he joined in 2002. Prof. Juang is also an Eminent Scholar of the Georgia Research Alliance.