Abstract
In this paper, a class of VQ-based discriminative kernel is proposed for speaker identification. Vector quantization is a well known method in speaker recognition, but its performance is not superior. The distortion of an utterance is accumulated, but the distortion source distribution on the codebook is discarded. We map an utterance to a vector by adopting the distribution and the average distortions on every code vector. Then the SVMs are used for classification. A one-versus-rest fashion is used for the problem of multiple classifications. Results on YOHO in text-independent case show that the method can improve the performance greatly and is comparative with the VQ and the basic GMM’s performances.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Vapnik, V.: Statistical Learning Theory. Johm Wiley and Sons, New York (1998)
Wan, V., Campbell, W.M.: Support Vector Machines for Speaker Verification and Identification. In: Proc. Neural Nerworks for Signal Processing X, pp. 775–784 (2000)
Jakkola, T.S., Haussler, D.: Exploiting generative models in discriminative classifiers. In: Kearns, M.S., Solla, S.A., Cohn, D.A. (eds.) Advances in Neural Information Processing System 11, MIT Press, Cambridge (1999)
Smith, N., Gales, M., Niranjan, M.: Data-dependent kernel in SVM classification of speech patterns. Tech.Rep. CUED/F-INFENG/TR.387, Cambridge University Engineering Department (2001)
Rosenberg, A.E., Soong, F.K.: Evaluation of a vector quantization talker recognition system in text independent and text dependent modes. Comput. Speech Lang. 22, 143–157 (1987)
Linde, Y., Buzo, A., Gray, R.M.: An algorithm for vector quantizer desigh. IEEE Trans. Commun. 20, 84–95 (1980)
Kohonen, T.: The self-organizing map. Proceedings of the IEEE 78, 1464–1480 (1990)
Fine, S., Navratil, J., Gopinath, R.A.: A hybrid GMM/SVM approach to speaker recognition. In: ICASSP (2001)
Shimodaira, H., Noma, K., Nakai, M., Sagayama, S.: Dynamic Time-Alignment Kernel in Support Vector Machine. In: NIPS, pp. 921–928 (2001)
Wan, V., Renals, S.: Valuaution of Kernel Methods for Speaker and Identification. In: Proc. ICASSP (2002)
Campbell, W.M.: Generalized Linear Discriminant Sequence Kernel For Speaker Recognition. In: Proc. ICASSP, pp. 161–164 (2002)
Burges, C.J.C.: A tutorial on Support Vector Machines for Pattern Recognition. Data Mining and Knowledge Discovery 2(2), 1–47 (1998)
Reynolds, D.A., Rose, R.C.: Robust text-independent speaker identification using Gaussian mixture speaker models. IEEE Trans. Speech Audio Processing 3, 72–83 (1995)
Platt, J.: Fast training of SVMs using sequential minimal optimisation. In: Advances in Kernel Methods: Support Vector Learing, pp. 185–208. MIT press, Cambridge (1999)
Schmidt, M., Gish, H.: Speaker Identification via Support Vector Machies. In: Proc. ICASSP, pp. 105–108 (1996)
Kinununen, T., Franti, P.: Speaker Discriminative Weighting Method for VQ-based Speaker Identification. In: Bigun, J., Smeraldi, F. (eds.) AVBPA 2001. LNCS, vol. 2091, pp. 150–156. Springer, Heidelberg (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lei, Z., Yang, Y., Wu, Z. (2005). Speaker Identification Using the VQ-Based Discriminative Kernels. In: Kanade, T., Jain, A., Ratha, N.K. (eds) Audio- and Video-Based Biometric Person Authentication. AVBPA 2005. Lecture Notes in Computer Science, vol 3546. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11527923_83
Download citation
DOI: https://doi.org/10.1007/11527923_83
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-27887-0
Online ISBN: 978-3-540-31638-1
eBook Packages: Computer ScienceComputer Science (R0)