next up previous contents
Next: About this document Up: No Title Previous: BRIEF DESCRIPTION OF

CVs OF KEY PROPOSERS

 

Dr. Luis B. Almeida

Luis B. Almeida graduated in Electrical Engineering by the Instituto Superior Tecnico, Lisbon, in 1972, and obtained a ``Doutor'' degree by the Universidade Tecnica de Lisboa, in 1983, with a thesis on nonstationary modeling of voiced speech. Since 1972, he has been with the Instituto Superior Tecnico, where he has recently been approved as ``Cathedratic Professor''. He has taught mathematics, telecommunications, digital systems, signal theory, discrete signal processing and neural networks. Currently he is responsible for the courses on signal theory, discrete signal processing and neural networks.

Since 1984 he has been head of the Neural Network and Signal Processing group of INESC (Instituto de Engenharia de Sistemas e Computadores). The main activities of this group, in the last few years, have been in the areas of neural networks (training algorithms and applications) and speech recognition (HMM/neural network based). He has authored a large number of scientific papers, one of which was awarded the ``IEEE Signal Processing Area ASSP Senior Award''. He was the president of the organizing committee of the 1990 EURASIP Workshop on Neural networks, held in Sesimbra, Portugal, in 1990. He is a member of IEEE and a founding member of ENNS (European Neural Network Society), in which he served as vice-president until the summer of 1994.

Number of Publications:

 
Papers in books                 		       4

Papers in scientific journals 13

Papers in scientific conferences 60

Co-editor of a book

Selected Publications:

``Non-Stationary Spectral Modelling of Voiced Speech,'' L.B. Almeida and J. M.Tribolet, IEEE Transactions on Acoustics, Speech and Signal Processing, vol. ASSP-31, no. 3, June 1983 (received the ``IEEE Signal Processing Area ASSP Senior Award'').

``A learning rule for asynchronous perceptrons with feedback in a combinatorial environment,'' L.B. Almeida, Proceedings of the IEEE First International Conference on Neural Networks, San Diego, CA, USA, June 1987.

``Speeding-Up Backpropagation,'' F.M. Silva and L.B. Almeida, in Rolf Eckmiller (ed.), Advanced Neural Computers, North-Holland, 1990.

``Adaptive Decorrelation,'' F.M. Silva and L.B. Almeida, in I. Aleksander and J. Taylor (eds.), Artificial Neural Networks 2, Elsevier Science Publishers, 1992.

``The Fractional Fourier Transform and Time-Frequency Representations,'' L.B. Almeida, IEEE Transactions on Signal Processing, vol. 42, no. 11, November 1994.

Dr. Hervé Bourlard

Hervé Bourlard received the Electrical and Computer Science Engineering degree and the Ph.D. degree in Applied Sciences, both from Faculté Polytechnique de Mons, Mons, Belgium, in 1982 and 1992, respectively.

From 1982 to 1990, he was a Research Scientist at the Philips Research Laboratory of Brussels, Belgium, where he worked on speech recognition and neural networks. From 1990 to 1994, he was an R&D Manager at L&H Speech Products, Belgium, where he continued his research activities on all aspects of speech recognition, language modeling, signal processing and speaker verification, turning some of the results into products.

From September 1988 to May 1989, he was on leave of absence from Philips at the International Computer Science Institute (ICSI), Berkeley, CA. Since then, he regularly goes on one-month visits to ICSI for collaborative projects. Since 1991, he has been an External Fellow of ICSI.

From August 1994 to December 1994, he was a full time Research Scientist at ICSI before joining Faculté Polytechnique de Mons, Mons, Belgium, in January 1995.

His current research interests include statistical pattern recognition, speech recognition, neural networks, and applied mathematics. He has authored/coauthored one book and over 70 refereed journal and conference papers.

Number of Publications:

 
Complete books   		 1

Papers in books 10

Papers in scientific journals 15

Papers in scientific conferences 45

Selected Publications:

``Statistical Inference in Multilayer Perceptrons and Hidden Markov Models with Applications in Continuous Speech Recognition,'' H. Bourlard, N. Morgan, and C.J. Wellekens, Neurocomputing: Algorithms, Architectures and Applications, F. Fogelman & J. Hérault (Eds.), NATO ASI Series, vol. F68, Springer-Verlag, pp. 217-226, 1990.

``Links Between Markov Models and Multilayer Perceptrons,'' H. Bourlard, H. and C.J. Wellekens, IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 12, no. 12, pp. 1167-1178, 1990.

``Continuous Speech Recognition by Connectionist Statistical Methods,'' H. Bourlard and N. Morgan, IEEE Trans. on Neural Networks, vol. 4, no. 6, pp. 893-909, 1993.

Connectionist Speech Recognition - A Hybrid Approach, H. Bourlard and Morgan, Kluwer Academic Publishers, ISBN 0-7923-9396-1, 1994.

``An Introduction to Connectionist Speech Recognition,'' N. Morgan and H. Bourlard, IEEE Signal Processing Magazine, pp. 25-42, May 1995.

``Neural Networks for Statistical Recognition of Continuous Speech,'' N. Morgan and H. Bourlard, Proceedings of the IEEE, vol. 83, no. 5, pp. 741-770, May 1995.

Dr. Nelson Morgan

Nelson Morgan received B.S., M.S., and Ph.D. degrees from the Electrical Engineering and Computer Sciences (EECS) Department at the University of California at Berkeley in 1977, 1979, and 1980 respectively.

From 1980 to 1984, he conducted and directed research in speech analysis, synthesis, and recognition, as well as DSP architectures, at National Semiconductor in Santa Clara. From 1984 to 1988 he worked at the EEG Systems Lab in San Francisco on the analysis of brain waves collected in controlled experiments on cognitive behaviors. In both jobs he developed connectionist approaches to signal analysis.

In 1988 he joined the International Computer Science Institute (ICSI), a non-profit research laboratory closely associated with the EECS Dept. at Berkeley. His position is that of a research scientist and group leader for the computer engineering department called the Realization Group. His current interests include the design of algorithms, architectures, and systems for parallel signal processing and pattern recognition systems, particularly using connectionist paradigms. In July of 1991 he also received an appointment as an Adjunct Professor in EECS at UC Berkeley. He organizes and teaches a course at Berkeley called ``Audio Signal Processing in Humans and Machines.''

Number of Publications:

 
Complete books   		 2

Papers in books 9

Papers in scientific journals 22

Papers in scientific conferences 63

Editor of a Computer Society collection of papers

Selected Publications:

Talking Chips: IC Speech Synthesis, N. Morgan, New York, McGraw-Hill, 1983.

``Applications of Neural Network (NN) Signal Processing in Brain Research,'' A. Gevins and N. Morgan, IEEE Trans. of the ASSP, vol. 36, no. 7, pp.1152-1161, July, 1988.

``The Ring Array Processor (RAP): A Multiprocessing Peripheral for Connectionist Applications,'' N. Morgan, J. Beck, P. Kohn, J. Bilmes, E. Allman, and J. Beer, Journal of Parallel and Distributed Computing, Special Issue on Neural Networks, 1992, vol. 14, pp.248-259, 1992.

``Stochastic Perceptual Auditory-Event-Based Models for Speech Recognition,'' N. Morgan, H. Bourlard, S. Greenberg, and H. Hermansky, Intl. Conference on Spoken Language Processing, pp 1943-1946, 1994.

``RASTA Processing of Speech,'' H. Hermansky and N. Morgan, IEEE Transactions on Speech and Audio Processing, special issue on Robust Speech Recognition, vol.2, no. 4, pp. 578-589, Oct., 1994.

``An Introduction to Connectionist Speech Recognition,'' N. Morgan and H. Bourlard, IEEE Signal Processing Magazine, pp. 25-42, May 1995.

``Neural Networks for Statistical Recognition of Continuous Speech,'' N. Morgan and H. Bourlard, Proceedings of the IEEE, vol. 83, no. 5, pp. 741-770, May 1995.

Dr. Steve Renals

Steve Renals obtained a first class BSc in Chemistry from Sheffield University in 1986. He then undertook graduate study at the University of Edinburgh, obtaining a MSc in Artificial Intelligence (1987) and a PhD in Physics (1991). The title of his PhD thesis was ``Speech and Neural Network Dynamics''; most of the research in this thesis was carried out at the Edinburgh University Centre for Speech Technology Research. From 1991--1992, he was a postdoctoral researcher at the International Computer Science Institute, Berkeley CA. In 1992, he was awarded a SERC Postdoctoral Fellowship, held at Cambridge University Engineering Department. At this time, he was also elected to a Research Fellowship at Darwin College, Cambridge. Since October 1994 he has been a lecturer in Computer Science at the Sheffield University, where he is also a member of the Institute for Language Speech and Hearing (ILASH).

Dr. Renals is the author/coauthor of over 30 papers in the areas of spoken language processing and neural computing. He is a member of the IEEE and ESCA (European Speech Communication Association). He was recently elected to the UK EPSRC College of Computing. His research interests include speech recognition, neural computing, language modeling and statistical approaches to representation, search and inference.

Number of Publications:

 
Papers in books                 		      7

Papers in scientific journals 5

Papers in scientific conferences 20

Selected Publications:

``Radial basis functions network for speech pattern classification,'' S. Renals, Electronics Letters, vol. 25, pp. 437-439, 1989.

``A study of network dynamics,'' S. Renals and R. Rohwer, Journal of Statistical Physics, vol. 58, pp. 825-847, 1990.

``Connectionist optimization of tied mixture hidden Markov models,'' S. Renals, H. Bourlard, N. Morgan, H. Franco and M. Cohen, Advances in Neural Information Processing Systems, vol. 4, J.E. Moody, S.J. Hanson and R.P. Lippmann (eds.), Morgan-Kaufmann, pp. 167-174, 1992.

``Connectionist probability estimators in HMM speech recognition,'' S. Renals, N. Morgan, H. Bourlard, M. Cohen and H. Franco, IEEE Transactions on Speech and Audio Processing, vol. 2, pp. 161-175, 1994.

``Efficient search using posterior phone probability estimates,'' S. Renals and M. Hochberg, Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing, 1995.

Dr. Tony Robinson

Anthony John Robinson obtained the BA in Natural Sciences in 1984, the Mphil in Computer Speech and Language Processing in 1986 and the PhD in connectionist speech recognition in 1989, all from Cambridge University. From 1984 to 1985 he was employed by G.E.C. Hirst Research Laboratories in the adaptive systems group. In 1989 he spent three months as an invited researcher at NTT Basic Research Laboratories, returning to take up a research assistant post in Cambridge University on the ESPRIT BRA ``Auditory Connectionist Techniques for Speech''. In 1991 he was appointed to an EPSRC Advanced Research Fellowship and in 1995 he will take the post of university lecturer.

His interests are in connectionist models, speech recognition, speech coding and reinforcement learning. He is an joint academic director of the annual ``Cambridge Neural Network Summer School'' that attracts about 100 participants.

Number of Publications:

 
Papers in books                 		      7

Papers in scientific journals 3

Papers in scientific conferences 17

Technical Reports 8

Selected Publications:

``Static and dynamic error propagation networks with application to speech coding,'' A.J. Robinson and F. Fallside, Neural Information Processing Systems, D.Z. Anderson, ed., American Institute of Physics, 1988.

``A recurrent error propagation network speech recognition system,'' T. Robinson and F. Fallside, Computer Speech and Language, vol. 5, pp. 259--274, July 1991.

``The application of recurrent nets to phone probability estimation,'' T. Robinson, IEEE Transactions on Neural Networks, March 1994.

``The use of recurrent networks in continuous speech recognition,'' Tony Robinson, Mike Hochberg and Steve Renals, Automatic Speech and Speaker Recognition -- Advanced Topics, C. H. Lee and K. K. Paliwal and F. K. Soong, Kluwer Academic Publishers, 1995.



next up previous contents
Next: About this document Up: No Title Previous: BRIEF DESCRIPTION OF



Jean-Marc Boite
Mon Dec 9 18:18:02 MET 1996