Comparison of speaker adaptation methods as feature extraction for SVM-based speaker recognition

IEEE Transactions on Audio, Speech and Language Processing

Volumn 18, Issue 6, 2010, Pages 1366-1378

  Ferras, Marc ^a   Leung, Cheung Chi ^b   Barras, Claude ^a   Gauvain, Jean Luc ^a  

^a CNRS   (France)

^b INSTITUTE FOR INFOCOMM RESEARCH   (Singapore)

Author keywords

Constrained MLLR (CMLLR); Gaussian mixture model (GMM); Gaussian supervectors; Maximum likelihood linear regression (MLLR); Speaker recognition; Support vector machine (SVM)

Indexed keywords

CONSTRAINED MLLR (CMLLR); GAUSSIAN MIXTURE MODEL; GAUSSIANS; SPEAKER RECOGNITION; SUPPORT VECTOR MACHINE (SVM);

FEATURE EXTRACTION; GAUSSIAN DISTRIBUTION; LINEAR REGRESSION; MATHEMATICAL TRANSFORMATIONS; MAXIMUM LIKELIHOOD; SUPPORT VECTOR MACHINES; VECTORS;

SPEECH RECOGNITION;

EID: 77955727653     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2009.2034187     Document Type: Article

References (33)

1. S. Kajarekar, N. Malayath, and H. Hermansky, "Analysis of speaker and channel variability in speech," in Proc. IEEE Workshop Speech Recognition and Understanding, Dec. 1999, pp. 59-62.
2. D. A. Reynolds, "Channel robust speaker verification via feature mapping," in Proc. Int. Conf. Acoust., Speech, Signal Process. (ICASSP), 2003, pp. 53-56.
3. P. Kenny and P. Dumouchel, "Experiments in speaker verification using factor analysis likelihood ratios," in Proc. IEEE Speaker Odyssey Workshop, Jun. 2004, pp. 219-226.
4. A. Solomonoff, C. Quillen, and W. M. Campbell, "Channel compensation for SVM speaker recognition," in Proc. IEEE Speaker Odyssey Workshop, 2004, pp. 57-62.
5. P. Auckenthaler, M. Carey, and H. Lloyd-Thomas, "Score normalization for text-independent speaker verification systems," Digital Signal Process., vol.10, pp. 42-54, 2000.
6. D. A. Reynolds, T. F. Quatieri, and R. B. Dunn, "Speaker verification using adapted Gaussian mixture models," Digital Signal Process., vol.10, pp. 19-41, 2000.
7. J. L. Gauvain and C. H. Lee, "Maximum a posteriori estimation for multivariate Guassian mixture observations of Markov chains," IEEE Trans. Speech Audio Process., vol.2, no.2, pp. 291-298, Apr. 1994.
8. R. Vogt, B. Baker, and S. Sridharan, "Modeling session variability in text-independent speaker verification," in Proc. Conf. Int. Speech Commun. Assoc. (INTERSPEECH), Lisbon, Portugal, 2005, pp. 3117-3120.
9. P. Kenny, G. Boulianne, P. Ouellet, and P. Dumouchel, "Joint factor analysis versus eigenchannels in speaker recognition," IEEE Trans. Audio, Speech, Lang. Process., vol.15, no.4, pp. 1435-1447, May 2007.
10. N. Dehak, R. Dehak, P. Kenny, and S. Sridharan, "Comparison between factor analysis and GMM support vector machines for speaker verification," in Proc. IEEE Speaker Odyssey Workshop, Stellenbosch, South Africa, 2008, paper 009.
11. W. M. Campbell, D. E. Sturim, and D. A. Reynolds, "Support vector machines using GMM supervectors for speaker verification," IEEE Signal Process. Lett., vol.13, no.5, pp. 308-311, May 2006.
12. A. Stolcke, L. Ferrer, S. Kajarekar, E. Shriberg, and A. Venkataraman, "MLLR transforms as features in speaker recognition," in Proc. Eur. Conf. Speech Commun. Technol. (EUROSPEECH), Sep. 2005, pp. 2425-2428.
13. A. Stolcke, L. Ferrer, and S. Kajarekar, "Improvements in MLLRtransform- based speaker recognition," in Proc. IEEE Speaker Odyssey Workshop, Jun. 2006, pp. 1-6.
14. M. Ferras, C. C. Leung, C. Barras, and J.-L. Gauvain, "MLLR techniques for speaker recognition," in Proc. IEEE Speaker Odyssey Workshop, Jan. 2008, pp. 21-24.
15. T. Anastasakos, J. McDonough, R. Schwartz, and J. Makhoul, "A compact model for speaker-adaptive training," in Proc. Int. Conf. Spoken Lang. Process. (ICSLP), Philadelphia, PA, 1996, vol.2, pp. 1137-1140.
16. M. Ferras, C. C. Leung, C. Barras, and J.-L. Gauvain, "Constrained MLLR for speaker recognition," in Proc. Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Apr. 2007.
17. C. J. Leggetter and P. C. Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models," Comput. Speech Lang., vol.9, pp. 171-185, 1995.
18. M. J. F. Gales and P. C. Woodland, "Mean and variance adaptation within the MLLR framework," Comput. Speech Lang., vol.10, no.4, pp. 249-264, Oct. 1996.
19. C. J. Leggetter and P. C.Woodland, "Flexible speaker adaptation using maximum likelihood linear regression," in Proc. ARPA Spoken Lang. Technol. Workshop, 1995, pp. 110-115.
20. V. V. Digalakis, D. Rtischev, and L. G. Neumeyer, "Speaker adaptation using constrained estimation of Gaussian mixtures," IEEE Trans. Speech Audio Process., vol.3, no.5, pp. 357-366, Sep. 1995.
21. C. J. C. Burges, "A tutorial on support vector machines for pattern recognition," Data Mining and Knowledge Discovery, vol.1, pp. 121-167, 1998.
22. A. Martin, G. Doddington, T. Kamm, M. Ordowski, and M. Przybocki, "The det curve in assessment of detection task performance," in Proc. Eur. Conf. Speech Commun. Technol. (EUROSPEECH), 1997, vol.4, pp. 1895-1898.
23. J. Pelecanos and S. Sridharan, "Feature warping for speaker verification," in Proc. IEEE Speaker Odyssey Workshop, 2001, pp. 213-218.
24. J. L. Gauvain, L. Lamel, H. Schwenk, G. Adda, L. Chen, and F. Lefevre, "Conversational telephone speech recognition," in Proc. Int. Conf. Acoust., Speech, Signal Process. (ICASSP), 2003, pp. 212-215.
25. W. M. Campbell, D. E. Sturim, D. A. Reynolds, and A. Solomonoff, "SVM based speaker verification using a GMMsupervector kernel and NAP variability compensation," in Proc. Int. Conf. Acoust., Speech, Signal Process. (ICASSP), 2006, pp. 97-100.
26. Z. N. Karam and W. M. Campbell, "A multi-class MLLR kernel for SVM speaker recognition," in Proc. Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Apr. 2008, pp. 4117-4120.
27. W. M. Campbell, "Generalized linear discriminant sequence kernels for speaker recognition," in Proc. Int. Conf. Acoust., Speech, Signal Process. (ICASSP), 2002, pp. 161-164.
28. B. Scholkopf, A. Smola, and K. R. Muller, "Kernel principal component analysis," in Advances in Kernel Methods-Support Vector Learning. Cambridge, U.K.: MIT Press, 1999.
29. C. Barras and J.-L. Gauvain, "Feature and score normalization for speaker verification of cellular data," in Proc. Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Hong Kong, April 2003, pp. II-49-II-52.
30. D. Matrouf, N. Scheffer, B. Fauve, and F. Bonastre, "A straightforward and efficient implementation of the factor analysis model for speaker verification," in Proc. Conf. Int. Speech Commun. Assoc. (INTERSPEECH), 2007, pp. 1242-1245.
31. J.-F. Bonastre, F. Wals, and S. Meigner, "Alize, a free toolkit for speaker recognition," in Proc. Int. Conf. Acoust., Speech, Signal Process. (ICASSP), 2005, pp. 737-740.
32. N. Brummer, "The Spescom DataVoice and University of Stellenbosch NIST SRE 2005 System," in NIST Speaker RecognitionWorkshop, Jun. 2005.
33. N. Brummer, L. Burget, J. H. Cernocky, O. Glembek, F. Grezl, M. Karafiat, D. A. van Leeuwen, P. Matejka, P. Schwarz, and A. Strasheim, "Fusion of heterogeneous speaker recognition systems in the STBU submission for the NIST speaker recognition evaluation 2006," IEEE Trans. Audio, Speech, Lang. Process., vol.15, no.7, pp. 2072-2084, Sep. 2007.