Transformation of Jacobian matrices for noisy speech recognition

Christophe Cerisara 1 Luca Rigazio 2 Robert Boman 2 Jean-Claude Junqua 2
1 PAROLE - Analysis, perception and recognition of speech
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : 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.
Type de document :
Communication dans un congrès
ICSLP'2000, 2000, none, 4 p, 2000
Liste complète des métadonnées

https://hal.inria.fr/inria-00099195
Contributeur : Publications Loria <>
Soumis le : mardi 26 septembre 2006 - 08:51:39
Dernière modification le : jeudi 11 janvier 2018 - 06:19:57

Identifiants

  • HAL Id : inria-00099195, version 1

Collections

Citation

Christophe Cerisara, Luca Rigazio, Robert Boman, Jean-Claude Junqua. Transformation of Jacobian matrices for noisy speech recognition. ICSLP'2000, 2000, none, 4 p, 2000. 〈inria-00099195〉

Partager

Métriques

Consultations de la notice

459