EXTENSION OF UNCERTAINTY PROPAGATION TO DYNAMIC MFCCs FOR NOISE ROBUST ASR - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

EXTENSION OF UNCERTAINTY PROPAGATION TO DYNAMIC MFCCs FOR NOISE ROBUST ASR

Dung Tran
  • Fonction : Auteur
  • PersonId : 953494
Denis Jouvet

Résumé

Uncertainty propagation has been successfully employed for speech recognition in nonstationary noise environments. The uncertainty about the features is typically represented as a diagonal covariance matrix for static features only. We present a framework for estimating the uncertainty over both static and dynamic features as a full covariance matrix. The estimated covariance matrix is then multiplied by scaling coefficients optimized on development data. We achieve 21\% relative error rate reduction on the 2nd CHiME Challenge with respect to conventional decoding without uncertainty, that is five times more than the reduction achieved with diagonal uncertainty covariance for static features only.

Domaines

Son [cs.SD]
Fichier principal
Vignette du fichier
extension_ICASSP2014.pdf (80.32 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-00954654 , version 1 (03-03-2014)
hal-00954654 , version 2 (11-03-2014)

Identifiants

  • HAL Id : hal-00954654 , version 1

Citer

Dung Tran, Emmanuel Vincent, Denis Jouvet. EXTENSION OF UNCERTAINTY PROPAGATION TO DYNAMIC MFCCs FOR NOISE ROBUST ASR. 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2014, Florence, Italy. ⟨hal-00954654v1⟩
483 Consultations
401 Téléchargements

Partager

Gmail Facebook X LinkedIn More