Amélioration des Performances des Systèmes Automatiques de Reconnaissance de la Parole pour la Parole Non Native - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2007

Amélioration des Performances des Systèmes Automatiques de Reconnaissance de la Parole pour la Parole Non Native

Résumé

In this article, we present an approach for non native automatic speech recognition (ASR). We propose two methods to adapt existing ASR systems to the non-native accents. The first method is based on the modification of acoustic models through integration of acoustic models from the mother tong. The phonemes of the target language are pronounced in a similar manner to the native language of speakers. We propose to combine the models of confused phonemes so that the ASR system could recognize both concurrent pronounciations. The second method we propose is a refinment of the pronounciation error detection through the introduction of graphemic constraints. Indeed, non native speakers may rely on the writing of words in their uttering. Thus, the pronounctiation errors might depend on the characters composing the words. The average error rate reduction that we observed is (22.5%) relative for the sentence error rate, and 34.5% (relative) in word error rate.
Fichier principal
Vignette du fichier
taima07.pdf (159.34 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

inria-00184565 , version 1 (06-11-2007)

Identifiants

  • HAL Id : inria-00184565 , version 1
  • ARXIV : 0711.1038

Citer

Ghazi Bouselmi, Dominique Fohr, Irina Illina, Jean-Paul Haton. Amélioration des Performances des Systèmes Automatiques de Reconnaissance de la Parole pour la Parole Non Native. Traitement et Analyse de l'Information : Méthodes et Applications - TAIMA'07, Jean-Paul Haton and Faouzi Ghorbel, May 2007, Hammamet, Tunisie. ⟨inria-00184565⟩
91 Consultations
126 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More