Characterizing Feature Variability in Automatic Speech Recognition Systems

Abstract : A method is described for predicting acoustic feature variability by analyzing the consensus and relative entropy of phoneme posterior probability distributions obtained with different acoustic models having the same type of observations. Variability prediction is used for diagnosis of automatic speech recognition (ASR) systems. When errors are likely to occur, different feature sets are considered for correcting recognition results. Experimental results are provided on the CH1 Italian portion of AURORA3.
Type de document :
Communication dans un congrès
International Conference on Acoustics, Speech and Language Processing, May 2006, Toulouse, France. V, pp.1029-1032, 2006
Liste complète des métadonnées

Littérature citée [11 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00433095
Contributeur : Loïc Barrault <>
Soumis le : mercredi 18 novembre 2009 - 10:40:59
Dernière modification le : mardi 19 juin 2018 - 11:51:51
Document(s) archivé(s) le : jeudi 17 juin 2010 - 20:47:49

Fichier

Barrault-ICASSP2006.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

  • HAL Id : hal-00433095, version 1

Collections

Citation

Loïc Barrault, Driss Matrouf, Renato De Mori, Roberto Gemello, Franco Mana. Characterizing Feature Variability in Automatic Speech Recognition Systems. International Conference on Acoustics, Speech and Language Processing, May 2006, Toulouse, France. V, pp.1029-1032, 2006. 〈hal-00433095〉

Partager

Métriques

Consultations de la notice

266

Téléchargements de fichiers

177