Computer Science – Computation and Language
Scientific paper
2007-11-07
Dans TAIMA'07, Traitement et Analyse de l'Information : M\'ethodes et Applications (2007)
Computer Science
Computation and Language
Scientific paper
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.
Bouselmi Ghazi
Fohr Dominique
Haton Jean-Paul
Illina Irina
No associations
LandOfFree
Amélioration des Performances des Systèmes Automatiques de Reconnaissance de la Parole pour la Parole Non Native does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Amélioration des Performances des Systèmes Automatiques de Reconnaissance de la Parole pour la Parole Non Native, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Amélioration des Performances des Systèmes Automatiques de Reconnaissance de la Parole pour la Parole Non Native will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-502357