Abstract : This paper presents a new approach to multi-band automatic speech recognition which has the advantage to overcome many limitations of classical muti-band systems. The principle of this new approach is to build a speech model in the time-frequency domain using the formalism of Bayesian networks. Contrarily to classical multi-band modeling, this formalism leads to a probabilistic speech model which allows communications between the different sub-bands and, consequently, no recombination step is required in recognition. We develop efficient learning and decoding algorithms and present illustrative experiments on a connected digit recognition task. The experiments show that the Bayesian network's approach is very promising in the field of noisy speech recognition.
https://hal.inria.fr/inria-00099452
Contributeur : Publications Loria
<>
Soumis le : mardi 26 septembre 2006 - 09:09:58
Dernière modification le : jeudi 11 janvier 2018 - 06:19:57
Document(s) archivé(s) le : mercredi 29 mars 2017 - 12:40:29
Khalid Daoudi, Dominique Fohr, Christophe Antoine. Réseaux Bayésiens Dynamiques pour la Reconnaissance Multi-Bandes de la Parole. XXIVe Journées d'Etudes sur la Parole - JEP'2002, Jun 2002, Nancy, France, 4 p, 2002. 〈inria-00099452〉
