Site menu:

Jean ROUAT

Jean ROUAT, Ph.D.

Full professor

Département de génie électrique et de génie informatique, Faculté de génie, Université de Sherbrooke, Jean.Rouat[at]Usherbrooke.ca

Adjunct Professor

Département de sciences biologiques, Faculté des arts et des sciences, Université de Montréal, Jean.Rouat[at]UMontreal.ca


Responsabilities and affiliations

Director of the European Research Consortium CHIST-ERA IGLU for the design of an autonomous intelligent agent that learns through interaction : on Interactive Grounded Language Understanding.

Full Member of CIRMMT Centre for Interdisciplinary Research in Music Media and Technology McGill Schulich School of Music, Faculté de musique de McGill Univ. : Sensory substitution (vision to audition and audition to vision).

Associate researcher, Institut National of Optic INO : Real time acquisition system and objects following with neural networks.

Member of the IEEE standard working group Ontological Standard for Ethically Driven Robotics and Automation Systems.

Founder of the inter-university research group in Computational Neurosciences and Intelligent Signal Processing NECOTIS

Member of international and scientific associations as IEEE, Int. Neural Network Society, Society for Neuroscience, Acoustical Society of America, Int. Speech Comm. Ass., etc.

Research Expert

Areae of research

Active Projects

These projects take part in the inter-university Computational Neurosciences and Intelligent Signal Processing research group (NECOTIS) in collaboration with international partners.

List of publications

Detailled list and downloads

Research

The research is in the intersection of Artificial Intelligence, Engineering and Neuroscience. We contribute to the research and development in the 3 areas. We conduct research on autonomous intelligent agents that learn in an unsupervised way in interaction with humans. We study new representations and features of signals (acoustical or visual) for real-time audio watermarking and protection, for multimodal scene analysis (object recognition and semantics of a scene) and recognition. We develop sources and interference separation systems with applications to robotics. We develop noninvasive intelligent prostheses for audition and vision. NECOTIS has access to up-to-date machine learning computing facilities and has an electrophysiological research lab for measures in the brain.

Short Bio

Jean Rouat holds a M.Sc. degree in Physics from Univ. de Bretagne, France (1981), an E. & E. M.Sc.A. degree in speech coding and speech recognition from Univ. Sherbrooke (1984) and an E. & E. Ph.D. in cognitive and statistical speech recognition jointly with Univ. de Sherbrooke and McGill Univ. (1988). His post-doc has been in psychoacoustics with the MRC, App. Psych. Unit, Cambridge, UK and in electrophysiology with the Institute of physi- ology, Lausanne, Switzerland. He is now with Univ. de Sherbrooke where he founded the Computational Neuroscience and Intelligent Signal Processing Research group (NECOTIS). He is also adjunct prof. in the biological sc. dep., Montreal Univ. His translational research links neuroscience and engineering for the creation of new technologies and a better understanding of learning multimodal representations. Development of hardware low power consumption Neural Processing Units for a sustainable development, interactions with artists for multimedia and musical creations are examples of transfers that he leads based on the knowledge he gains from neuroscience. He is leading funded projects to develop sensory substitution and intelligent systems. He is also leading an interdisciplinary CHIST-ERA european consortium (IGLU - Interactive Grounded Language Understanding) for the development of an intelligent agent that learns through interaction.

Contacts

Université de Sherbrooke, Faculté de génie, Département de génie électrique et de génie informatique
2500, boul. de l'Université
Sherbrooke, Québec   Canada
J1K 2R1
courriel: jean.rouat[at]usherbrooke.ca ou jean.rouat[at]umontreal.ca