EQUALIZING SUB-BAND ERROR RATES IN SPEAKER RECOGNITION

5th European Conference on Speech Communication and Technology, EUROSPEECH 1997

Volumn , Issue , 1997, Pages 2303-2306

  Auckenthaler, Roland ^a   Mason, John S ^b  

^a GRAZ UNIVERSITY OF TECHNOLOGY   (Austria)

^b UNIVERSITY OF WALES   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

EQUALIZERS; SPEECH COMMUNICATION; SPEECH RECOGNITION;

BAND SPLITTING; ERROR RATE; FREQUENCY WARPING; FULL BAND; MEL FREQUENCIES; MULTIPLE-PATH; RECOGNITION ACCURACY; SPEAKER RECOGNITION; SUBBANDS; WARPING FUNCTION;

ERRORS;

EID: 85019604081     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (5)

1. H. Hermansky, S. Tibrewala, and M. Pavel. Towards ASR on partially corrupted speech. In Proc. ICSLP-96, volume 1, pages 462-65, 1996.
2. H. Bourlard and S. Dupont. A new ASR approach on independent processing and recombination of partial frequency bands. In Proc. ICSLP-96, volume 1, pages 426-429, 1996.
3. L. Besacier and J. Bonastre. Subband approach for automatic speaker recognition. In Proc. AVBPA-97, pages 195-202, 1997.
4. J. B. Allen. How do humans recognize speech? IEEE Trans. Speech and Audio Processing, 2(4):pages 567-577, October 1994.
5. L. Xu and J.S. Mason. Optimization of perceptually-based spectral transforms in speaker identification. In Proc. Eurospeech-91, pages 439^142, 1991.