A Bayesian network for time-frequency speech modeling and recognition - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2001

A Bayesian network for time-frequency speech modeling and recognition

Abstract

In this paper, we propose a new speech model which is a Bayesian network (BN) built in the time-frequency domain. Contrarily to HMMs, this BN provides a good modeling of the frequency dynamics, particularly the asynchrony between sub-bands. The experiments we carried out show that, consequently, speech is modeled with higher fidelity. Moreover, our new model allows to perform multi-band speech recognition without {\it all} the drawbacks of the usual multi-band approach where each sub-band is independently modeled by a HMM. This makes our model very suited to the case where speech is corrupted by a band-limited noise. We present experiments on an isolated digit recognition task, in clean and noisy conditions. The results we obtain show that the BNs framework is very promising in the field of speech modeling and recognition.
No file

Dates and versions

inria-00100524 , version 1 (26-09-2006)

Identifiers

  • HAL Id : inria-00100524 , version 1

Cite

Khalid Daoudi, Dominique Fohr, Christophe Antoine. A Bayesian network for time-frequency speech modeling and recognition. International Conference on Artificial Intelligence and Soft Computing, May 2001, Cancun, Mexico, 5 p. ⟨inria-00100524⟩
120 View
0 Download

Share

Gmail Facebook Twitter LinkedIn More