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.
Murat Deviren, Khalid Daoudi. Continuous Speech Recognition using Structural Learning of Dynamic Bayesian Networks. XI European Signal Processing Conference - EUSIPCO 2002, Sep 2002, Toulouse, France, 4 p. ⟨inria-00100855⟩