Spatio-Temporal and Complex-Valued Models based on SOM map applied to Speech Recognition

Zouhour Neji Ben Salem 1 Laurent Bougrain 2 Frédéric Alexandre 2
2 CORTEX - Neuromimetic intelligence
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : Speech perception and recognition using biologically inspired models is a challenging issue not well explored yet. The paper presents two spatiotemporal biologically inspired methods for the preprocessing and learning of speech signal based on SOM (Self Organization Map). The experimental results are very encouraging and provide a framework which could be more studied to overcome present limitation of speech perception and recognition technology.
Type de document :
Communication dans un congrès
Twentieth International Joint Conference on Artificial Intelligence - IJCAI'2007, Jan 2007, Hyderabad, India. 2007
Liste complète des métadonnées

https://hal.inria.fr/inria-00118122
Contributeur : Laurent Bougrain <>
Soumis le : lundi 4 décembre 2006 - 11:53:17
Dernière modification le : jeudi 11 janvier 2018 - 06:19:48

Identifiants

  • HAL Id : inria-00118122, version 1

Collections

Citation

Zouhour Neji Ben Salem, Laurent Bougrain, Frédéric Alexandre. Spatio-Temporal and Complex-Valued Models based on SOM map applied to Speech Recognition. Twentieth International Joint Conference on Artificial Intelligence - IJCAI'2007, Jan 2007, Hyderabad, India. 2007. 〈inria-00118122〉

Partager

Métriques

Consultations de la notice

399