Statistical Adaptation of Acoustic Models to Noise Conditions for Robust Speech Recognition

Angel De La Torre 1 Dominique Fohr 1 Jean-Paul Haton 1
1 PAROLE - Analysis, perception and recognition of speech
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : Noise degrades the performance of Automatic Speech Recognition (ASR) systems working in real condition. The mismatch between the training and recognition conditions is considered the main factor involved in this degradation, and most methods for robust ASR are focussed on its minimization. In this work, we compare robust methods for ASR based on (a) the compensation of the noise effects and (b) the adaptation of the acoustic models to noise con-ditions. We propose a method for the adaptation of the acoustic models to the noise conditions based on a statistical formulation. In this method, each Gaussian is adapted to the noisy environment according to the estimated noise conditions. Recognition experiments have been carried out using speech acquired in real car environments. The results show the statistical formulation for adaptation provides an accurate method for robust ASR.
Mots-clés : speech recognition ronustness noise reconnaissance de la parole adapatation bruit robustesse
Type de document :
Communication dans un congrès
International Conference on Spoken Language Processing - ICSLP 2002, 2002, Denver, USA, pp.1437-1440, 2002
Liste complète des métadonnées
https://hal.inria.fr/inria-00100832
Contributeur : Publications Loria <>
Soumis le : mardi 26 septembre 2006 - 14:52:13
Dernière modification le : jeudi 11 janvier 2018 - 06:19:55

Identifiants

  • HAL Id : inria-00100832, version 1

Collections

INRIA | LORIA | UNIV-LORRAINE

Citation

Angel De La Torre, Dominique Fohr, Jean-Paul Haton. Statistical Adaptation of Acoustic Models to Noise Conditions for Robust Speech Recognition. International Conference on Spoken Language Processing - ICSLP 2002, 2002, Denver, USA, pp.1437-1440, 2002. 〈inria-00100832〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

199

Contact


archive-ouverte@inria.fr