Transformation of Jacobian matrices for noisy speech recognition - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2000

Transformation of Jacobian matrices for noisy speech recognition

Résumé

Robustness of automatic speech recognition systems to noise is still an issue, especially for small footprint systems. This paper addresses the problem of noise robustness using model compensation. Jacobian adaptation is an example of model compensation, which is also computationally efficient. However, its performance drops when the mismatch between training and testing environments increases. Our new adaptation algorithm is based on finding the best linear transformation for compensating the mismatch between training and testing conditions. In this paper, it is shown that, using a dimensionality reduction technique, time and memory requirements of the algorithm can be further decreased compared to the classical Jacobian adaptation. Furthermore, experimental results for an English digit recognition task, recorded in a car at 60 mph, show that the error rate decreases by 66 %, compared to the classical Jacobian adaptation.

Domaines

Autre [cs.OH]
Fichier non déposé

Dates et versions

inria-00099195 , version 1 (26-09-2006)

Identifiants

  • HAL Id : inria-00099195 , version 1

Citer

Christophe Cerisara, Luca Rigazio, Robert Boman, Jean-Claude Junqua. Transformation of Jacobian matrices for noisy speech recognition. ICSLP'2000, 2000, none, 4 p. ⟨inria-00099195⟩
213 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More