THE USE OF META-HMM IN MULTISTREAM HMM TRAINING FOR AUTOMATIC SPEECH RECOGNITION

5th International Conference on Spoken Language Processing, ICSLP 1998

Volumn , Issue , 1998, Pages

  Wellekens, C J ^a   Kangasharju, J ^a   Milesi, C ^a  

^a EURECOM   (France)

Author keywords

[No Author keywords available]

Indexed keywords

AUTOMATIC SPEECH RECOGNITION; HMM TRAINING; MULTI-STREAM; MULTI-STREAM HMM; PARALLEL STREAMS; PARTIAL INFORMATION; ROBUSTNESS TO NOISE; TEST SIGNAL;

SPEECH RECOGNITION;

EID: 85128406196     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (4)

1. H. Bourlard, S. Dupont, H. Hermansky, N. Morgan, "Towards sub-band-based speech recognition," in Proc. of European Signal Processing Conference, (Trieste, Italy), pp. 1579-1582, Sept. 1996.
2. H. Bourlard, S. Dupont, "A new ASR approach based on independent processing and recombination of partial frequency bands," in Proc. of Intl. Conf. on Spoken Language Processing, (Philadelphia, USA), pp. 422-425, Oct. 1996.
3. H. Bourlard, S. Dupont, C. Ris, "Multistream speech recognition," Tech. Rep. IDIAP-RR 96-07, IDIAP, Martigny, Switzerland, 1996.
4. S.Dupont, H.Bourlard, "Using Multiple Tiem Scales in a Multi-stream Speech Recognition System", Proc. Eurospeech 1997, vol 1, pp.3, Rhodes Greece, 1997