Towards Neurocomputational Speech and Signal Processing

Date: 
Fri, 2007-06-29 10:00 - 11:30

Nu vrijdag 29 juni om 10:00 uur geeft Prof. Jean Rouat van de Université de Sherbrooke, Canada, een voordracht over spraak- en signaalverwerking met klassieke technieken en gepulste neurale netwerken in zaal Shannon. Iedereen is welkom, het belooft interessant te worden.

Een abstract van de voordracht en een korte biografie van de spreker staan hieronder.
---------------------

Abstract:

'Towards Neurocomputational Speech and Signal Processing'

From physiology we learn that the auditory system extracts simultaneous features from the underlying signal, giving birth to simultaneous representations of audible signals. We also learn that pattern analysis and recognition are not separated processes (in opposition to the engineering approach of pattern recognition where analysis and recognition are usually separated processes). Also, in the visual system, it has been observed that the sequence order of firing is crucial to perform fast visual recognition tasks (Rank Order Coding). The use of the Rank Order Coding has also been recently hypothesized in the mammalian auditory system.

Dr. Rouat will present exploratory and potential solutions to applications in speech and image processing with networks of spiking neurons (simple models of 'real' neurons). In one application he will present a very simplistic speech recognition prototype that uses the Rank Order Coding scheme and will discuss its performance in comparison with a conventional Hidden Markov Model speech recognizer.

In another application, he will explain how to combine an auditory images representation with a network of oscillatory spiking neurones to segregate and bind auditory objects for acoustical source separation. It is shown that the spiking neural network performs unsupervised auditory images segmentation (to find 'auditory' objects) and binding of the objects belonging to the same auditory source (yielding automatic sound source separation).

Dr. Rouat will also briefly comment on the use of the Oscillatory Dynamic Link Matcher for applications in image processing.

Biography:

Jean Rouat was visiting the CEE departement at McMaster Univ. and the département de sciences biologiques from Université de Montréal during is sabbatical leave from Université de Sherbrooke (Sept. 2006 to August 2007).

He holds a master degree in physics from Univ. de Bretagne, France (1981), an E. & E. master degree in speech coding and speech recognition from Université de Sherbrooke (1984) and an E. & E. Ph.D. in cognitive and statistical speech recognition jointly with Université de Sherbrooke and McGill University (1988). From 1988 to 2001 he was with Université du Québec à Chicoutimi (UQAC); in 1995 and 1996, he was on a sabbatical leave with the Medical Research Council, Applied Psychological Unit, Cambridge, UK and the Institute of Physiology, Lausanne, Switzerland. In 1990 he founded the ERMETIS, Microelectronics and Signal Processing Research Group from UQAC. He is now with Université de Sherbrooke where he founded the Computational Neuroscience and Intelligent Signal Processing Research group. He regularly acts as a reviewer for speech, neural networks and signal processing journals. He is an active member of scientific associations (Acoustical Society of America, Int. Speech Communication, IEEE, Int. Neural Networks Society, Association for Research in Otolaryngology, etc.). He is a senior member of the IEEE and served on the IEEE technical committee on Machine Learning for Signal Processing from 2001 to 2005.