Continuous Multi-Band Speech Recognition using Bayesian Networks - Inria - Institut national de recherche en sciences et technologies du numérique
Communication Dans Un Congrès Année : 2001

Continuous Multi-Band Speech Recognition using Bayesian Networks

Khalid Daoudi
Dominique Fohr

Résumé

Using the Bayesian networks framework, we present a new multi-band approach for continuous speech recognition. This new approach has the advantage to overcome all the limitations of the standard multi-band techniques. Moreover, it leads to a higher fidelity speech modeling than HMMs. We provide a preliminary evaluation of the performance of our new approach on a connected digits recognition task.

Domaines

Autre [cs.OH]
Fichier principal
Vignette du fichier
A01-R-226.pdf (88.75 Ko) Télécharger le fichier
Loading...

Dates et versions

inria-00107521 , version 1 (19-10-2006)

Identifiants

  • HAL Id : inria-00107521 , version 1

Citer

Khalid Daoudi, Dominique Fohr, Christophe Antoine. Continuous Multi-Band Speech Recognition using Bayesian Networks. IEEE Automatic Speech Recognition and Understanding Workshop - ASRU'2001, IEEE, Dec 2001, Trento, Italy, 4 p. ⟨inria-00107521⟩
109 Consultations
154 Téléchargements

Partager

More