Data-driven temporal filters and alternatives to GMM in speaker verification

Digital Signal Processing: A Review Journal

Volumn 10, Issue 1, 2000, Pages 55-74

  Malayath, Narendranath ^a   Hermansky, Hynek ^a,b   Kajarekar, Sachin ^a   Yegnanarayana, B ^c  

^a OREGON HEALTH AND SCIENCE UNIVERSITY   (United States)

^b INTERNATIONAL COMPUTER SCIENCE INSTITUTE   (United States)

^c INDIAN INSTITUTE OF TECHNOLOGY MADRAS   (India)

Author keywords

[No Author keywords available]

Indexed keywords

DIGITAL FILTERS; MATHEMATICAL MODELS; PATTERN RECOGNITION SYSTEMS; TELEPHONE SETS;

DATA DRIVEN TEMPORAL FILTERS; GAUSSIAN MIXTURE MODELS (GMM); SPEAKER VERIFICATION SYSTEMS;

SPEECH RECOGNITION;

EID: 0033885411     PISSN: 10512004     EISSN: None     Source Type: Journal    
DOI: 10.1006/dspr.1999.0363     Document Type: Article

References (22)

1. Atal B. S. Automatic recognition of speakers from their voices. Proc. IEEE. 64:1974;460-475.
2. Avendano C., Hermansky H. On the properties of temporal processing for speech in adverse environments. Proceedings of 1997 Workshop on Applications of Signal Processing to Audio and Acoustics. 1997;Mohonk Mountain House, New York. p. 1-12.
3. Diamantaras K. I., Kung S. Y. Principal Component Neural Networks - Theory and Applications. 1996;Wiley, New York.
4. Doddington G. R. Speaker recognition evaluation - an overview and perspective. Proc. of Speaker Recognition and its Commercial and Forensic Applications, France. 1998;. p. 60-66.
5. Furui S. Speaker-independent isolated word recognition based on emphasized spectral dynamics. Proc. ICASSP, Tokyo, Japan. 1986;. p. 1991-1994.
6. Hermansky H. Perceptual linear predictive (PLP) analysis of speech. JASA. 87:1990;1738-1752.
7. Hermansky H. Should recognizers have ears? Speech Commun. 25:1998;3-27.
8. Hermansky H., Morgan N. RASTA processing of speech. IEEE Trans. Speech Audio Process. 2:1995;578-589.
9. Hornik K., Stinchcombe M., White H. Multilayer networks are universal approximators. Neural Networks. 2:1989;359-378.
10. Malayath N., Hermansky H., Kain A. Towards decomposing the sources of variability in speech. Proc. EUROSPEECH-97, Greece. 1997;. p. 497-500.
11. Martin A., Przybocki M. The NIST 1999 speaker recognition evaluation - An overview. Digital Signal Processing. 10:2000;1-18.
12. Mermelstein P. Distance measures for speech recognition, psychological and instrumental. Chen R C. H. Pattern Recognition and Artificial Intelligence. 1976;Academic Press, New York.
13. Przybocki M. A., Martin A. F. NIST speaker recognition evaluation - 1997. Proc. of Speaker Recognition and its Commercial and Forensic Applications, Avignon, France. 1998;. p. 120-123.
14. Reynolds D. A. Speaker identification and verification using gaussian mixture models. Speech Commun. 17:1995;91-108.
15. Reynolds D. A. Comparison of background normalization methods for text-independent speaker verification. Proc. EUROSPEECH-97, Greece. 1997;. p. 963-966.
16. Reynolds D. A. HTIMIT and LLHDB: Speech corpora for the study of handset transducer effects. Proc. ICASSP, Munich. 1997;. p. 1535-1538.
17. Reynolds D. A., Quatieri T. F., Dunn R. B. Speaker verification using adapted Gaussian mixture models. Digital Signal Processing. 10:2000;19-41.
18. Schwarz R., Anastasakos T., Kubala F., Makhoul J., Nguyen L., Zavaliagkos G. Comparitive experiments on large vocabulary speech recognition. Proc. of ARPA Workshop on Human Language Technology, Plainsboro, NJ. 1993;. p. 1-12.
19. Sharma S., Vermeulen P., Hermansky H. Combining information from multiple classifiers for speaker verification. Proc. of Speaker Recognition and its Commercial and Forensic Applications, France. 1998;. p. 115-119.
20. Umesh S., Cohen L., Nelson D. Frequency-warping and speaker-normalization. Proc. of ICASSP-97, Munich, Germany. 1997;. p. 983-987.
21. van Vuuren S. Speaker Recognition in a Time-Feature Space. 1999;Oregon Graduate Institute of Science and Technology, Portland.
22. van Vuuren S., Hermansky H. !MESS, a modular efficient speaker verification system. Proc. of Speaker Recognition and its Commercial and Forensic Applications, France. 1998;. p. 198-201.