Project : metiss
Section: Overall Objectives
The research objectives of the METISS research group are dedicated to the audio signal and speech processing and are organised along three axes: speaker characterization, information detection and tracking in audio streams and "advanced" processing of audio signals (in particular, source separation). Some aspects of speech recognition (modeling and decoding) are also addressed so as to reinforce these three principal topics.
The main industrial sectors in relation with the topics of the METISS research group are the telecommunication sector (with voice authentification), the Internet and multi-media sector (with audio indexing), the musical and audio-visual production sector (with audio signal processing), and the sector of educational softwares, games and toys.
In addition to the dissemination of our work through publications in conferences and journals, our scientific activity is accompanied with the permanent concern of measuring our progress within the framework of evaluation campaigns, to disseminate software resources which we develop and to share our efforts with other partner laboratories.
On a regular basis, METISS is involved in bilateral or multilateral partnerships, within the framework of consortia (ELISA), networks (HASSIP), working groups (GDR ISIS), national research projects (Domus Videum, Technolangues) European projects (BANCA) and industrial contracts with various companies (Thomson Multi-Media, France Télécom R&D, ...).