Spatio-Temporal and Complex-Valued Models based on SOM map applied to Speech Recognition - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2007

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

Zouhour Neji Ben Salem
  • Fonction : Auteur
Laurent Bougrain
Frédéric Alexandre

Résumé

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.
Fichier non déposé

Dates et versions

inria-00118122 , version 1 (04-12-2006)

Identifiants

  • HAL Id : inria-00118122 , version 1

Citer

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. ⟨inria-00118122⟩
192 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More