Automatic Speech Recognition for African Languages with Vowel Length Contrast

Abstract : This paper deals with ASR for two languages: Hausa and Wolof. Their common characteristic is to appear with vowel length contrast. In other words, two versions (short / long) of a same vowel exist in the phoneme inventory of the language. We expect that taking into account this contrast in ASR models might help and this is what we investigate in this pilot study. The experimental results show that while both approaches (vowel length contrast modeling or not) lead to similar results, their combination allows to slightly improve ASR performance. As a by-product of ASR system design, we also show that the acoustic models obtained allow a large scale analysis of vowel length contrast for phonetic studies.
Type de document :
Communication dans un congrès
5th Workshop on Spoken Language Technologies for Under-resourced Languages (SLTU), May 2016, Yogyakarta, Indonesia. Procedia computer science, 〈10.1016/j.procs.2016.04.041〉
Liste complète des métadonnées

Littérature citée [18 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01350040
Contributeur : Laurent Besacier <>
Soumis le : vendredi 29 juillet 2016 - 15:02:44
Dernière modification le : jeudi 11 octobre 2018 - 08:48:03

Fichier

sltu_gauthier.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

Collections

Citation

Elodie Gauthier, Laurent Besacier, Sylvie Voisin. Automatic Speech Recognition for African Languages with Vowel Length Contrast. 5th Workshop on Spoken Language Technologies for Under-resourced Languages (SLTU), May 2016, Yogyakarta, Indonesia. Procedia computer science, 〈10.1016/j.procs.2016.04.041〉. 〈hal-01350040〉

Partager

Métriques

Consultations de la notice

195

Téléchargements de fichiers

370