Structural Learning of Dynamic Bayesian Networks in Speech Recognition

Murat Deviren 1 Khalid Daoudi 1
1 PAROLE - Analysis, perception and recognition of speech
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : We present a speech modeling methodology where no a priori assumption is made on the dependencies between the observed and the hidden speech processes. Rather, dependencies are learned form data. This methodology guaranties improvement in modeling fidelity compared to HMMs. In addition, it gives the user a control on the trad-off between modeling accuracy and model complexity. Furthermore, the approach is technicaly very attractive because all the computational effort is made in the traning phase.
Type de document :
Communication dans un congrès
7th European Conference on Speech Communication and Technolgoy - EUROSPEECH'2001, Sep 2001, Aalborg, Denmark, 4 p, 2001
Liste complète des métadonnées

https://hal.inria.fr/inria-00100526
Contributeur : Publications Loria <>
Soumis le : mardi 26 septembre 2006 - 14:46:28
Dernière modification le : jeudi 11 janvier 2018 - 06:19:55

Identifiants

  • HAL Id : inria-00100526, version 1

Collections

Citation

Murat Deviren, Khalid Daoudi. Structural Learning of Dynamic Bayesian Networks in Speech Recognition. 7th European Conference on Speech Communication and Technolgoy - EUROSPEECH'2001, Sep 2001, Aalborg, Denmark, 4 p, 2001. 〈inria-00100526〉

Partager

Métriques

Consultations de la notice

245