Objectif When one considers human performance as our target, universal automatic recognition of speech is far from a solved problem. This seems to be related by a large amount to feature extraction, modelling and adaptability weaknesses, as discussed in recognized publications. Strikingly, these weaknesses remain fully in the case of clean speech in known conditions, emphasizing deficiencies in dealing with intrinsic speech variabilities and extracting information form the signal itself. This has however been partly hidden by the more pressing problem of making state-of-the-art systems usable in real noisy situations, under constrained tasks, with the implicit target of reaching "clean speech" performance, with deserved success.The goal of DIVINES is to develop some new knowledge towards renewed feature extraction and modelling techniques that would have better capacities, particularly in handling speech intrinsic variabilities. First, human and machine performance and the effect of intrinsic variabilities will be compared based on a diagnostic procedure. The outcomes of this analysis will then be exploited to target feature extraction, acoustic and lexical modelling. Compatibility with techniques dealing with noise and integration within current systems are also part of the objectives.The project is relevant to the "multimodal interfaces" objective as it concerns more accurate and adaptable recognition of spoken language. This is central to the concept of multimodal man-machine interaction where the speech understanding service is likely to remain an independent component in a modular design. Advances in this field could be decisive in realizing the vision of natural interactivity. Programme(s) FP6-IST - Information Society Technologies: thematic priority under the specific programme "Integrating and strengthening the European research area" (2002-2006). Thème(s) IST-2002-2.3.1.6 - Multimodal interfaces Appel à propositions Data not available Régime de financement STREP - Specific Targeted Research Project Coordinateur MULTITEL Contribution de l’UE Aucune donnée Adresse PARC INITIALIS, COPERNIC AVENUE 1 7000 MONS Belgique Voir sur la carte Coût total Aucune donnée Participants (8) Trier par ordre alphabétique Trier par contribution de l’UE Tout développer Tout réduire BABEL TECHNOLOGIES S.A. Belgique Contribution de l’UE Aucune donnée Adresse BOULEVARD DOLEZ 33 7000 MONS Voir sur la carte Coût total Aucune donnée CARL VON OSSIETZKY UNIVERSITAET OLDENBURG Allemagne Contribution de l’UE Aucune donnée Adresse AMMERLAENDER HEERSTRASSE 114-118 26129 OLDENBURG Voir sur la carte Coût total Aucune donnée FRANCE TELECOM SA France Contribution de l’UE Aucune donnée Adresse PLACE D'ALLERAY 6 75015 PARIS Voir sur la carte Coût total Aucune donnée INSTITUT EURECOM France Contribution de l’UE Aucune donnée Adresse 2229 ROUTE DES CRETES - SOPHIA ANTIPOLIS 06560 VALBONNE Voir sur la carte Coût total Aucune donnée LOQUENDO SPA Italie Contribution de l’UE Aucune donnée Adresse VIA VALDELLATORRE 4 10100 TORINO Voir sur la carte Coût total Aucune donnée POLITECNICO DI TORINO Italie Contribution de l’UE Aucune donnée Adresse CORSO DUCA DEGLI ABRUZZI 24 10129 TORINO Voir sur la carte Coût total Aucune donnée THE ROYAL INSTITUTION FOR THE ADVANCEMENT OF LEARNING (MCGILL UNIVERSITY) Canada Contribution de l’UE Aucune donnée Adresse JAMES ADMINISTRATION BUILDING, 845 SHERBROOKE ST. WEST H3A 2T5 MONTREAL (QC) Voir sur la carte Coût total Aucune donnée UNIVERSITE D'AVIGNON ET DU PAYS-VAUCLUSE France Contribution de l’UE Aucune donnée Adresse RUE LOUIS PASTEUR 74 84029 AVIGNON Voir sur la carte Coût total Aucune donnée