Objectif The ACORNS project intends to develop, implement and test the mathematical models and computational mechanisms needed to create an artificial agent that is capable of acquiring human verbal communication behaviour based on the memory-prediction theory of intelligence. Unlike conventional pattern recognizers, the ACORNS agent will learn dynamic emergent patterns of speech and non-speech sounds from rich and redundant representations of the acoustic input. Learning will be guided by the intention to fulfil basic needs required to acquire the verbal and non-verbal communication skills of a toddler.To reach the goal, advances in understanding and realisation are needed in five closely interrelated areas, (1) representations of acoustic signals in multiple parallel temporal and spectral resolutions, (2) methods for patterning signals into coherent structures that correspond to potentially meaningful acoustic events, (3) methods for building and maintaining dynamic emergent patterns in memory, (4) methods for searching in an associative memory, and (5) methods for handling natural interaction between an artificial agent and a human, including verbal and non-verbal (affective) information.In addition to fundamental scientific knowledge ACORNS will also produce novel techniques that will be integrated and tested into more conventional systems that perform pattern recognition and human-machine interaction. By doing so, ACORNS remedies important weaknesses in today's state-of-the-art speech recognition and dialogue systems.It is intended that ACORNS will provide a radical new approach to the creation of artificial systems capable of human-like communicative behaviour. Champ scientifique natural sciencesphysical sciencesacousticsnatural sciencescomputer and information sciencesartificial intelligencepattern recognitionnatural sciencesmathematicsapplied mathematicsmathematical model Programme(s) FP6-IST - Information Society Technologies: thematic priority under the specific programme "Integrating and strengthening the European research area" (2002-2006). Thème(s) 2.3.4.1 b9 - 2.3.4.1.b9 FET open Appel à propositions Data not available Régime de financement STREP - Specific Targeted Research Project Coordinateur STICHTING KATHOLIEKE UNIVERSITEIT Contribution de l’UE Aucune donnée Adresse GEERT GROOTEPLEIN-NOORD 9 6525 EZ NIJMEGEN Pays-Bas Voir sur la carte Coût total Aucune donnée Participants (4) Trier par ordre alphabétique Trier par contribution de l’UE Tout développer Tout réduire KATHOLIEKE UNIVERSITEIT LEUVEN Contribution de l’UE Aucune donnée Adresse Voir sur la carte Liens Site web Opens in new window Coût total Aucune donnée KUNGLIGA TEKNISKA HOGSKOLAN Suède Contribution de l’UE Aucune donnée Adresse VALHALLAVAGEN 79 100 44 STOCKHOLM Voir sur la carte Coût total Aucune donnée TEKNILLINEN KORKEAKOULU Finlande Contribution de l’UE Aucune donnée Adresse OTAKAARI 1 02015 ESPOO Voir sur la carte Coût total Aucune donnée THE UNIVERSITY OF SHEFFIELD Contribution de l’UE Aucune donnée Adresse Voir sur la carte Liens Site web Opens in new window Coût total Aucune donnée
