Continuous multi-band speech recognition using Bayesian networks

2001 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2001 - Conference Proceedings

Volumn , Issue , 2001, Pages 41-44

  Daoudi, K ^a   Fohr, D ^a   Antoine, C ^a  

^a LORIA   (France)

Author keywords

[No Author keywords available]

Indexed keywords

BAYESIAN NETWORKS; CONTINUOUS SPEECH RECOGNITION; SPEECH;

CONNECTED DIGITS; MULTI BAND; NEW APPROACHES; SPEECH MODELING;

SPEECH RECOGNITION;

EID: 84962892151     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ASRU.2001.1034584     Document Type: Conference Paper

References (8)

1. H. Bourlard and S. Dupont. A new ASR approach based on independent processing and recombination of partial frequency bands. ICSLP'96.
2. H. Hermansky et al. Towards ASR on partially corrupted speech. ICSLP'96.
3. B. C. J. Moore. An introduction to the psychology of hearing. Academic Press, London, 1989.
4. K. Daoudi, D. Fohr, and C. Antoine. A new approach for multi-band speech recognition based on probabilistic graphical models. ICSLP'2000.
5. G. Zweig. Speech recognition with dynamic Bayesian networks. PhD thesis, Univ. California, Berkeley, 1998.
6. G. Gravier, M. Sigelle, and G. Chollet. A markov random field based multi-band model. ICASSP'2000.
7. A.P. Dawid. Applications of a general propagation algorithm for probabilistic expert systems. Statistics and Computing, (2):25-36, 1992.
8. F.V. Jensen and S.L. Lauritzen and K.G. Olsen. Bayesian updating in recursive graphical models by local computations. Computational Statistics and Data Analysis, (4):269-282, 1990.