Title: Continuous Multi-Band Speech Recognition using Bayesian Networks

Authors: Khalid Daoudi, Dominique Fohr, Christophe Antoine

Abstract: 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.

a01kd047.ps a01kd047.pdf