Merging of Native and Non-native Speech for Low-resource Accented ASR

Abstract : This paper presents our recent study on low-resource automatic speech recognition (ASR) system with accented speech. We propose multi-accent Subspace Gaussian Mixture Models (SGMM) and accent-specific Deep Neural Networks (DNN) for improving non-native ASR performance. In the SGMM framework, we present an original language weighting strategy to merge the globally shared parameters of two models based on native and non-native speech respectively. In the DNN framework, a native deep neural net is fine-tuned to non-native speech. Over the non-native baseline, we achieved relative improvement of 15 % for multi-accent SGMM and 34 % for accent-specific DNN with speaker adaptation.
Type de document :
Communication dans un congrès
3rd International Conference on Statistical Language and Speech Processing, SLSP 2015, Nov 2015, Budapest, Hungary. Statistical Language and Speech Processing, 9449, 2015, Statistical Language and Speech Processing. 〈http://grammars.grlmc.com/SLSP2015/〉. 〈10.1007/978-3-319-25789-1_24〉
Liste complète des métadonnées

Littérature citée [24 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01289140
Contributeur : Benjamin Lecouteux <>
Soumis le : lundi 29 janvier 2018 - 10:57:21
Dernière modification le : jeudi 11 octobre 2018 - 08:48:03
Document(s) archivé(s) le : vendredi 25 mai 2018 - 10:31:53

Fichier

SLSP2015-sarah.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Sarah Samson Juan, Laurent Besacier, Benjamin Lecouteux, Tien-Ping Tan. Merging of Native and Non-native Speech for Low-resource Accented ASR. 3rd International Conference on Statistical Language and Speech Processing, SLSP 2015, Nov 2015, Budapest, Hungary. Statistical Language and Speech Processing, 9449, 2015, Statistical Language and Speech Processing. 〈http://grammars.grlmc.com/SLSP2015/〉. 〈10.1007/978-3-319-25789-1_24〉. 〈hal-01289140〉

Partager

Métriques

Consultations de la notice

189

Téléchargements de fichiers

72