Exploiting confidence measures for missing data speech recognition

Christophe Cerisara 1
1 PAROLE - Analysis, perception and recognition of speech
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : Automatic speech recognition in highly non-stationary noise, for instance with a competing speaker or background music, is an extremely challenging and still unsolved problem. Missing data recognition is a robust approach that is well adapted to this kind of noise. A standard missing data technique consists in marginalizing out, from the observation likelihoods computed during decoding, the contribution of the spectro-temporal fragments that are dominated by noise. However, such an approach can hardly be applied to advanced parameterization domains that do not separate speech from noise frequencies, such as the cepstrum or ETSI AFE. We propose in the work to extend this technique to such parameterization domains, and not only to spectrographic-like front-ends as it was the case before. This is realized by masking the observations that favor erroneous decoding paths, instead of masking the features that are dominated by noise. These new missing data "masks" are now estimated based on speech recognition confidence measures, which can be considered as indicators of the reliability of decoding paths. A first version of this robust algorithm is evaluated on the French broadcast news ESTER corpus.
Type de document :
Communication dans un congrès
Proceedings on Acoustics'08, Jul 2008, Paris, France. 2008
Liste complète des métadonnées

Littérature citée [17 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00330726
Contributeur : Christophe Cerisara <>
Soumis le : mercredi 10 décembre 2008 - 10:45:24
Dernière modification le : vendredi 9 février 2018 - 13:20:01
Document(s) archivé(s) le : lundi 7 juin 2010 - 18:27:15

Fichier

acoustics08.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00330726, version 1

Collections

Citation

Christophe Cerisara. Exploiting confidence measures for missing data speech recognition. Proceedings on Acoustics'08, Jul 2008, Paris, France. 2008. 〈inria-00330726〉

Partager

Métriques

Consultations de la notice

242

Téléchargements de fichiers

113