inria-00099452, version 1
Réseaux Bayésiens Dynamiques pour la Reconnaissance Multi-Bandes de la Parole
Khalid Daoudi
a, 1Dominique Fohr b, 1Christophe Antoine c, 1
XXIVe Journées d'Etudes sur la Parole - JEP'2002 (2002) 4 p
Résumé : 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.
- a – INRIA
- b – CNRS
- c – MIC2
- 1 : PAROLE (INRIA Lorraine - LORIA)
- INRIA – CNRS : UMR7503 – Université Henri Poincaré - Nancy I – Université Nancy II – Institut National Polytechnique de Lorraine (INPL)
- Domaine : Informatique/Autre
- Mots-clés : speech recognition – bayesian networks || reconnaissance de la parole – réseaux bayésiens
- Référence interne : A02-R-257 || daoudi02d
- Commentaire : Colloque avec actes et comité de lecture. nationale.
- inria-00099452, version 1
- http://hal.inria.fr/inria-00099452
- oai:hal.inria.fr:inria-00099452
- Contributeur : Publications Loria
- Soumis le : Mardi 26 Septembre 2006, 09:09:58
- Dernière modification le : Jeudi 28 Septembre 2006, 15:22:46
Exporter