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 Contributor : Publications LoriaConnect in order to contact the contributor Submitted on : Tuesday, September 26, 2006 - 9:09:58 AM Last modification on : Friday, February 26, 2021 - 3:28:06 PM Long-term archiving on: : Wednesday, March 29, 2017 - 12:40:29 PM
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, Equipe Parole - LORIA, Jun 2002, Nancy, France, 4 p. ⟨inria-00099452⟩