EUSIPCO'2002 banner

Paper data
Continuous Speech Recognition Using Structural Learning of Dynamic Bayesian Networks

Deviren Murat, INRIA
Daoudi Khalid, INRIA

Page numbers in the proceedings:
Volume III pp 599-602

Language and Speech Recognition

Paper abstract
We present a new continuous automatic speech recognition system where no a priori assumptions on the dependencies between the observed and the hidden speech processes are made. Rather, dependencies are learned form data using the Bayesian networks formalism. This approach guaranties to improve modelling fidelity as compared to HMMs. Furthermore, our approach is technically very attractive because all the computational effort is made in the training phase.

A PDF version is available here