Multiple Pronunciation Generation using Grapheme-to-Phoneme Conversion based on Conditional Random Fields

Irina Illina 1 Dominique Fohr 1 Denis Jouvet 1
1 PAROLE - Analysis, perception and recognition of speech
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : We propose an approach to grapheme-to-phoneme conversion with multiple pronunciations based on a probabilistic method: Conditional Random Fields (CRF). CRF give a long term prediction and assume relaxed state independence condition compared to HMMs. Moreover, we propose an algorithm to one-to-one letter to phoneme alignment needed for CRF training. This alignment is based on discrete HMM. This paper investigated the impact of the training set size and the multiple pronunciation generation. Validated on BDLex French dictionary, our approach compares favorably with the performance of the state-of-the-art Joint-Multigram Models in term of the quality of the pronunciations and in term of recall and precision measures for multiple pronunciation variants generation.
Type de document :
Communication dans un congrès
XIV International Conference "Speech and Computer" (SPECOM'2011), Sep 2011, Kazan, Russia. 2011
Liste complète des métadonnées

https://hal.inria.fr/inria-00616325
Contributeur : Denis Jouvet <>
Soumis le : lundi 22 août 2011 - 10:34:21
Dernière modification le : jeudi 11 janvier 2018 - 06:19:56

Identifiants

  • HAL Id : inria-00616325, version 1

Collections

Citation

Irina Illina, Dominique Fohr, Denis Jouvet. Multiple Pronunciation Generation using Grapheme-to-Phoneme Conversion based on Conditional Random Fields. XIV International Conference "Speech and Computer" (SPECOM'2011), Sep 2011, Kazan, Russia. 2011. 〈inria-00616325〉

Partager

Métriques

Consultations de la notice

345