Impact of Pronunciation Variant Frequency on Automatic Non-Native Speech Segmentation - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2011

Impact of Pronunciation Variant Frequency on Automatic Non-Native Speech Segmentation

Résumé

This paper investigates the quality of the automatic phonetic segmentation of non-native speech with respect to the amount of pronunciation variants that are used in the pronunciation lexicon, in view of exploiting such segmentation for providing automatic prosodic feedback for computer assisted foreign language learning. The selection of the pronunciation variants in the lexicon was controlled according to the amount of times the variants were observed in non-native speech from other speakers. Keeping all the variants that were observed at least one time in other non-native speaker data, leads to the worst results, confirming the fact that introducing unusual pronunciation variants in the lexicon is also harmful for non-native speech segmentation. Overall best results are obtained when keeping all the variants observed at least two times. This seems a good trade-off to have a large number of variants, and at the same time avoiding unusual variants.
Fichier non déposé

Dates et versions

hal-00639118 , version 1 (08-11-2011)

Identifiants

  • HAL Id : hal-00639118 , version 1

Citer

Denis Jouvet, Larbi Mesbahi, Anne Bonneau, Dominique Fohr, Irina Illina, et al.. Impact of Pronunciation Variant Frequency on Automatic Non-Native Speech Segmentation. 5th Language & Technology Conference - LTC'11, Nov 2011, Poznan, Poland. pp.145-148. ⟨hal-00639118⟩
259 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More