Structural Learning of Dynamic Bayesian Networks in Speech Recognition - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2001

Structural Learning of Dynamic Bayesian Networks in Speech Recognition

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.
No file

Dates and versions

inria-00100526 , version 1 (26-09-2006)

Identifiers

  • HAL Id : inria-00100526 , version 1

Cite

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. ⟨inria-00100526⟩
144 View
0 Download

Share

Gmail Facebook X LinkedIn More