Fusion of Multiple Uncertainty Estimators and Propagators for Noise Robust ASR

Dung Tien Tran 1 Denis Jouvet 2 Emmanuel Vincent 2
1 PAROLE - Analysis, perception and recognition of speech
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
2 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : Uncertainty decoding has been successfully used for speech recognition in highly nonstationary noise environments. Yet, accurate estimation of the uncertainty on the denoised signals and propagation to the features remain difficult. In this work, we propose to fuse the uncertainty estimates obtained from different uncertainty estimators and propagators by linear combination. The fusion coefficients are optimized by minimizing a measure of divergence with oracle estimates on development data. Using the Kullback-Leibler divergence, we obtain 18\% relative error rate reduction on the 2nd CHiME Challenge with respect to conventional decoding, that is about twice as much as the reduction achieved by the best single uncertainty estimator and propagator.
Type de document :
Communication dans un congrès
2014 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2014, Florence, Italy. 2014
Liste complète des métadonnées

Littérature citée [21 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00955185
Contributeur : Dung Tran <>
Soumis le : mardi 11 mars 2014 - 16:10:30
Dernière modification le : jeudi 11 janvier 2018 - 06:27:31
Document(s) archivé(s) le : mercredi 11 juin 2014 - 12:51:52

Fichier

Icassp2014_fusion.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00955185, version 2

Citation

Dung Tien Tran, Denis Jouvet, Emmanuel Vincent. Fusion of Multiple Uncertainty Estimators and Propagators for Noise Robust ASR. 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2014, Florence, Italy. 2014. 〈hal-00955185v2〉

Partager

Métriques

Consultations de la notice

595

Téléchargements de fichiers

233