Book Prizes
- AY 01/02
- AY02/03
- AY03/04

Invited Talks

Scalable Self-organizing Peer-to-Peer Systems
A Neural-Perception Based Approach to Automatic Speech Recognition
A Gentle Introduction to the Theory of Computation

Title : Scalable Self-organizing Peer-to-Peer Systems

Speaker : Prof Seif Haridi, Visiting Professor, Department of Computer Science, School of Computing, NUS

Date : 6 November 2003, Thursday

Time : 3.00pm - 4.00pm

Venue: Video Conference Room, S15-04-30, School of Computing, NUS

Chairperson : Prof Teo Yong Meng

Abstract
In this talk we give an introduction to current research in Peer to Peer systems. We focus on Structured Peer to Peer systems based on the concept of Distributed Hash Tables (DHS). We describe as an example of modern Peer-to-Peer systems DKS (Distributed K-ary Search) a self-organizing DHT with low communication overhead, and as an example of self-organizing service we show a broadcast service.

About the Speaker
Seif Haridi is leading a research group at the Royal Institute of Technology (Kungliga Tekniska Högskolan), KTH and the Swedish Institute of Computer Science, SICS in the area of distributed computer systems. The activities include Peer-to-Peer computing, programming languages design and implementation for distributed and parallel computing, middleware of distributed computing, distributed and highly available systems. He is a codesigner of the programming language Oz and the Mozart programming platform (see http://www.mozart-oz.org/). Seif Haridi has done earlier research on implementation of logic and constraint-based languages including SICStus Prolog and AKL (Andorra Kernel Language), and on scalable cache-coherent parallel computers. He is a co-inventor of COMA architectures, a scalable cache-coherent multiprocessor with only caches. This concept has been taken by SUN Microsystems. He is the scientific coordinator of the current EU project PEPITO on peer-to-peer systems.

Title : A Neural-Perception Based Approach to Automatic Speech Recognition

Speaker : Professor Lee Chin Hui, Georgia Institute of Technology

Date : 24 September 2003, Wednesday

Time : 10.00am

Venue : Video Conference Room, S15, Level 4

Chairperson : Professor Chua Tat Seng

Abstract
Spectrum and cepstrum based signal features have been used extensively in today’s automatic speech recognition (ASR) systems. They map acoustics to linguistics indirectly. In this talk we explore knowledge-based features and their applications to ASR. These features are usually associated with some acoustic and linguistic attributes or events, such as frication and nasality, which could be used to facilitate direct interpretation of speech. We first show that these events could be obtained using artificial neural networks, a strong link with auditory perception. Using this event lattice directly detected from the speech signal, we could potentially design next generation speech recognition algorithms that are more robust and perform better than state-of-the-art ASR systems. These features not only provide key diagnostic information and useful constraints but also work well with the prevailing pattern matching paradigm in the ASR community. We illustrate this point by integrating a knowledge-based front-end with a hidden Markov model based (HMM) back-end and show that such an ASR system achieved a 20% word error rate reduction over the best Wall Street Journal results reported in literature. We believe this new set of features could serve as a missing link to bring together different speech research areas, including analysis, synthesis, perception, production and recognition. Many new research opportunities are yet to be explored.

About the Speaker
Chin-Hui Lee is a professor at School of Electrical and Computer Engineering. Dr Lee received the B.S. degree in Electrical Engineering from National Taiwan University, Taipei, in 1973, the M.S. degree in Engineering and Applied Science from Yale University, New Haven, in 1977, and the Ph.D. degree in Electrical Engineering with a minor in Statistics from University of Washington, Seattle, in 1981.

After graduation, Dr Lee joined Verbex Corporation, Bedford, MA, and was involved in research on connected word recognition. In 1984, he became affiliated with Digital Sound Corporation, Santa Barbara, where he engaged in research and product development in speech coding, speech synthesis, speech recognition and signal processing for the development of the DSC-2000 Voice Server. Between 1986 and 2001, he was with Bell Laboratories, Murray Hill, New Jersey, where he became a Distinguished Member of Technical Staff and Director of the Dialogue Systems Research Department. His research interests include multimedia communication, multimedia signal and information processing, speech and speaker recognition, speech and language modeling, spoken dialogue processing, adaptive and discriminative learning, biometric authentication, information retrieval, and bioinformatics. His research scope is reflected in "Automatic Speech and Speaker Recognition: Advanced Topics", published by the Kluwer Academic Publishers in 1996. From August 2001 to August 2002 he was a visiting professor at the School of Computing, National University of Singapore. In September 2002, he joined the Faculty of School of Electrical and Computer Engineering at Georgia Institute of Technology.

Dr Lee has participated actively in professional societies. He is a member of the IEEE Signal Processing Society, Communication Society, and the European Speech Communication Association. He is also a lifetime member of the Computational Linguistics Society in Taiwan. In 1991-1995, he was an associate editor for the IEEE Transactions on Signal Processing and Transactions on Speech and Audio Processing. During the same period, he served as a member of the ARPA Spoken Language Coordination Committee. In 1995-1998 he was a member of the Speech Processing Technical Committee of the IEEE Signal Processing Society (SPS), and later became the chairman of the Speech TC from 1997 to 1998. In 1996, he helped promote the SPS Multimedia Signal Processing (MMSP) Technical Committee in which he is a founding member.

Dr Lee is a Fellow of the IEEE, and has published more than 250 papers and 25 patents on the subject of automatic speech and speaker recognition. He received the SPS Senior Award in 1994 and the SPS Best Paper Award in 1997 and 1999, respectively. In 1997, he was also awarded the prestigious Bell Labs President's Gold Award for his contributions to the Lucent Speech Processing Solutions product. In 2000, he was named one of the six Distinguished Lecturers by the IEEE Signal Processing Society.

Title : A Gentle Introduction to the Theory of Computation

Speaker : Professor J. Nievergelt, ETH Zurich and NUS

Date : 14 August 2003, Thursday

Time : 11.00am

Venue : Video-conferencing Room, S15, Level 4

Chairperson : Dr Tan Kian Lee

Abstract
Education in the sciences is based on fundamental, timeless concepts, laws and principles. In contrast, computer science education often emphasizes product specific hands-on skills. Practical skills are undoubtedly essential, but if they are not backed up by conceptual knowledge they are of short-lived utility.

The theory of computation addresses one of the fundamental problems of computer science: what can or cannot be computed using given means, and at what cost. Novices are easily frightened by the abstract, mathematical nature of this theory. We have developed software packages that support the detailed study of examples using animation and step-by-step feedback during the solution of exercises. This talk and demo shows examples of concepts, problems and solutions used in a large-enrollment compulsory introduction to the theory of computation course.

About the Speaker
J. Nievergelt is a Professor of Computer Science at ETH, Zurich, Switzerland. He has been an Adjunct Professor at NUS CS dept for the past 3 years. His research interests are in algorithms and data structures, parallel computation, and interactive systems. He received his PhD in 1965 from the University of Illinois (UIUC), and has been a professor at UIUC and Chairman of the Dept of Computer Science at the University of North Carolina at Chapel Hill. He has held visiting appointments at industrial research labs and universities world wide. He has written several books and many papers in his areas of interest, and has been on the editorial board of prestigious journals.