A General Method for Combining Acoustic Features in an Automatic Speech Recognition System

Abstract : A general method for the use of different types of fea- tures in Automatic Speech Recognition (ASR) systems is presented. A gaussian mixture model (GMM) is ob- tained in a reference acoustic space. A specific fea- ture combination or selection is associated to each gaus- sian of the mixture and used for computing symbol pos- terior probabilities. Symbols can refer to phonemes, phonemes in context or states of a Hidden Markov Model (HMM). Experimental results are presented of applications to phoneme and word rescoring after verification. Two corpora were used, one with small vocab- ularies in Italian and Spanish and one with very large vocabulary in French.
Type de document :
Communication dans un congrès
ITRW on Speech Recognition and Intrinsic Variation, May 2006, Toulouse, France. pp.N/A, 2006
Liste complète des métadonnées

Littérature citée [26 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00433108
Contributeur : Loïc Barrault <>
Soumis le : mercredi 18 novembre 2009 - 11:02:39
Dernière modification le : mardi 19 juin 2018 - 11:51:51
Document(s) archivé(s) le : jeudi 17 juin 2010 - 20:48:43

Fichier

Matrouf-SRIV2006.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00433108, version 1

Collections

Citation

Driss Matrouf, Loïc Barrault, Renato De Mori. A General Method for Combining Acoustic Features in an Automatic Speech Recognition System. ITRW on Speech Recognition and Intrinsic Variation, May 2006, Toulouse, France. pp.N/A, 2006. 〈hal-00433108〉

Partager

Métriques

Consultations de la notice

209

Téléchargements de fichiers

113