Advertisement

A Critical Comparison between GMM Classifier and Polynomial Classifier for Text-Independent Speaker Identification

  • Nirmalya SenEmail author
  • T. K. Basu
Chapter
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 133)

Abstract

This paper compares performances between Gaussian Mixture Model (GMM) classifier and polynomial classifier for text-independent speaker identification. The MFCC feature set has been used for this comparison. Experimental evaluation was conducted on the POLYCOST database with 130 speakers. The importance of the prior in the polynomial classifier has been discussed in detail. Results reveal that, the identification accuracy of the polynomial classifier strongly depends on the choice of prior. For proper prior selection the polynomial classifier can perform better than the GMM classifier.

Keywords

Speaker identification GMM classifier Polynomial classifier 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Davis, S.B., Mermelsteine, P.: Comparison of parametric representation for monosyllabic word recognition in continuously spoken sentences. IEEE Trans. Acoust., Speech, Signal Processing, ASSP-28(4), 357–365 (1980)CrossRefGoogle Scholar
  2. 2.
    Reynolds, D.A., Rose, R.C.: Robust Text-Independent speaker identification using Gaussian mixture speaker models. IEEE Trans. Speech and Audio Processing 3(1), 72–83 (1995)CrossRefGoogle Scholar
  3. 3.
    Campbell, W.M., Assaleh, K.T., Broun, C.C.: Speaker recognition with polynomial classifiers. IEEE Trans. Speech and Audio Processing 10(4), 205–212 (2002)CrossRefGoogle Scholar
  4. 4.
    Campbell, W.M., Torkkola, K., Balakrishnan, S.V.: Dimension reduction techniques for training polynomial networks. In: Proceedings of 17 International Conference of Machine Learning, vol. 200, pp. 1015–1022Google Scholar
  5. 5.
    Petrovska, D., et al.: POLYCOST: A Telephonic speech database for speaker recognition. In: RLA2C, Avignon, France, April 20-23, pp. 211–214 (1998)Google Scholar

Copyright information

© Springer-Verlag GmbH Berlin Heidelberg 2012

Authors and Affiliations

  1. 1.Signal Processing Research GroupC.E.T, IIT KharagpurKharagpurIndia
  2. 2.ITME, AMIRAKolkataIndia

Personalised recommendations