Grapheme To Phoneme Conversion - An Arabic Dialect Case

Salima Harrat 1 Karima Meftouh 2 Mourad Abbas 3 Kamel Smaïli 4
1 SMART
ENS Bouzaréah-Alger - École normale supérieure - Bouzaréah-Alger
2 Université d'Annaba
LRI-ANNABA - Laboratoire de Recherche en Informatique
3 SMART
CRSTDLA - Centre de Recherche Scientifique et Technique pour le Dévelopement de la Langue Arabe
4 SMarT - Statistical Machine Translation and Speech Modelization and Text
LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : We aim to develop a speech translation system between Modern Standard Arabic and Algiers dialect. Such a system must include a Text-to-Speech module which itself must include a grapheme-phoneme converter. Algiers dialect is an Arabic dialect concerned by the most problems of Modern Standard Arabic in NLP area. Furthermore, it could be considered as an under-resourced language because it is a vernacular language for which no substantial corpus exists. In this paper we present a grapheme-to-phoneme converter for this language. We used a rule based approach and a statistical approach, we got an accuracy of 92% VS 85% despite the lack of resource for this language.
Type de document :
Communication dans un congrès
Spoken Language Technologies for Under-resourced Languages, May 2014, Saint Petesbourg, Russia. 2014
Liste complète des métadonnées

Littérature citée [10 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01067022
Contributeur : Kamel Smaïli <>
Soumis le : lundi 22 septembre 2014 - 17:55:49
Dernière modification le : mardi 24 avril 2018 - 13:33:28
Document(s) archivé(s) le : mardi 23 décembre 2014 - 11:50:50

Fichier

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

Identifiants

  • HAL Id : hal-01067022, version 1

Collections

Citation

Salima Harrat, Karima Meftouh, Mourad Abbas, Kamel Smaïli. Grapheme To Phoneme Conversion - An Arabic Dialect Case. Spoken Language Technologies for Under-resourced Languages, May 2014, Saint Petesbourg, Russia. 2014. 〈hal-01067022〉

Partager

Métriques

Consultations de la notice

338

Téléchargements de fichiers

465