Using the FASST source separation toolbox for noise robust speech recognition

Alexey Ozerov 1 Emmanuel Vincent 1
1 METISS - Speech and sound data modeling and processing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : We describe our submission to the 2011 CHiME Speech Separation and Recognition Challenge. Our speech separation algorithm was built using the Flexible Audio Source Separation Toolbox (FASST) we developed recently. This toolbox is an implementation of a general flexible framework based on a library of structured source models that enable the incorporation of prior knowledge about a source separation problem via user-specifiable constraints. We show how to use FASST to develop an efficient speech separation algorithm for the CHiME dataset. We also describe the acoustic model training and adaptation strategies we used for this submission. Altogether, as compared to the baseline system, we obtain an improvement of keyword recognition accuracies in all conditions. The best improvement of about 40 % is achieved in the worst condition of -6 dB Signal-to-Noise-Ratio (SNR), where 18 % of this improvement is due to the speech separation. The improvement decreases when the SNR increases. These results indicate that audio source separation can be very helpful to improve speech recognition in noisy or multi-source environments.
Type de document :
Communication dans un congrès
International Workshop on Machine Listening in Multisource Environments (CHiME 2011), Sep 2011, Florence, Italy. 2011
Liste complète des métadonnées

https://hal.inria.fr/inria-00598734
Contributeur : Alexey Ozerov <>
Soumis le : mardi 7 juin 2011 - 14:26:46
Dernière modification le : jeudi 11 janvier 2018 - 06:20:09
Document(s) archivé(s) le : vendredi 9 septembre 2011 - 15:17:12

Fichier

CHiME_submission_v4.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00598734, version 1

Collections

Citation

Alexey Ozerov, Emmanuel Vincent. Using the FASST source separation toolbox for noise robust speech recognition. International Workshop on Machine Listening in Multisource Environments (CHiME 2011), Sep 2011, Florence, Italy. 2011. 〈inria-00598734〉

Partager

Métriques

Consultations de la notice

321

Téléchargements de fichiers

236