A RECOMBINATION STRATEGY FOR MULTI-BAND SPEECH RECOGNITION BASED ON MUTUAL INFORMATION CRITERION

6th European Conference on Speech Communication and Technology, EUROSPEECH 1999

Volumn , Issue , 1999, Pages 603-606

  Okawa, Shigeki ^a   Nakajima, Takehiro ^b   Shirai, Katsuhiko ^b  

^a CHIBA INSTITUTE OF TECHNOLOGY   (Japan)

^b WASEDA UNIVERSITY   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

SPEECH COMMUNICATION; SPEECH RECOGNITION;

ACOUSTIC ENVIRONMENT; AMOUNT OF INFORMATION; AUTOMATIC SPEECH RECOGNITION; INFORMATION CRITERION; MULTI BAND; MUTUAL INFORMATIONS; NOISY SPEECH; RECOGNITION ACCURACY; RECOMBINATION PROCESS; SUBBANDS;

INFORMATION THEORY;

EID: 0004078041     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (6)

1. H. Bourlard and S. Dupont. A new ASR approach based on independent processing and recombination of partial frequency bands. In Proc. Int. Conf. on Spoken Language Processing, pages 426-429, Philadelphia, October 1996.
2. S. Tibrewala and H. Hermansky. Sub-band based recognition of noisy speech. In Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, pages 1255-1258, Munich, April 1997.
3. S. Okawa, E. Bocchieri and A. Potamianos. Multi-band speech recognition in noisy environments. In Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, pages 641-644, Seattle, May 1998.
4. N. Mirghafori and N. Morgan. Combining connectionist multi-band and full-band probability streams for speech recognition of natural numbers. In Proc. Int. Conf. on Spoken Language Processing, pages 743-746, Sydney, December 1998.
5. J. B. Allen. How do humans process and recognize speech? IEEE Trans. on Speech and Audio Processing, 2(4):567-577, October 1994.
6. Y. Normandin, R. Cardin, and R. DeMori. High-performance connected digit recognition using maximum mutual information estimation. IEEE Trans. on Speech and Audio Processing, 2(2):299-311, April 1994.