R{\'e}seaux Bay{\'e}siens Dynamiques pour la Reconnaissance Multi-Bandes de la Parole
Khalid Daoudi and Dominique Fohr and Christophe Antoine. ( 2002 )
in: XXIVe Journ{\'e}es d'Etudes sur la Parole - JEP'2002, Equipe Parole - LORIA, pages 4 p
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.
Download / Links
BibTeX Reference
@inproceedings{daoudi:inria-00099452, 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.}, address = {Nancy, France}, author = {Daoudi, Khalid and Fohr, Dominique and Antoine, Christophe}, booktitle = {{XXIVe Journ{\'e}es d'Etudes sur la Parole - JEP'2002}}, hal_id = {inria-00099452}, hal_local_reference = {A02-R-257 || daoudi02d}, hal_version = {v1}, keywords = {bayesian networks ; reconnaissance de la parole ; speech recognition ; r{\'e}seaux bay{\'e}siens}, month = {June}, note = {Colloque avec actes et comit{\'e} de lecture. nationale.}, organization = {{Equipe Parole - LORIA}}, pages = {4 p}, pdf = {https://hal.inria.fr/inria-00099452/file/A02-R-257.pdf}, title = {{R{\'e}seaux Bay{\'e}siens Dynamiques pour la Reconnaissance Multi-Bandes de la Parole}}, url = {https://hal.inria.fr/inria-00099452}, year = {2002} }