Design of Cubic Spline Wavelet for Open Set Speaker Classification in Marathi

  • Hemant A. Patil
  • T. K. Basu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4274)


In this paper, a new method of feature extraction based on design of cubic spline wavelet has been described. Dialectal zone based speaker classification in Marathi language has been attempted in the open set mode using polynomial classifier. The method consists of dividing the speech signal into nonuniform subbands in approximate Mel-scale using an admissible wavelet packet filterbank and modeling each dialectal zone with the 2nd and 3rd order polynomial expansions of feature vector. Confusion matrices are also shown for different dialectal zones.


Order Approximation Confusion Matrix Wavelet Packet Speaker Recognition Indian Language 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Campbell, W.M., Assaleh, K.T., Broun, C.C.: Speaker recognition with polynomial classifiers. IEEE Trans. on Speech and Audio Processing 10, 205–212 (2002)CrossRefGoogle Scholar
  2. 2.
    Coifman, R.R., Meyer, Y., Wickerhauser, M.V.: Wavelet analysis and signal processing. In: Boston, J., Ruskai, B.B., et al. (eds.) Wavelets and Applications, pp. 153–178 (1992)Google Scholar
  3. 3.
    Davis, S.B., Mermelstein, P.: Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans. Acoust., Speech and Signal Processing 28, 357–366 (1980)CrossRefGoogle Scholar
  4. 4.
    Erzin, E., Cetin, A.E., Yardimci, Y.: Subband analysis for robust speech recognition in the presence of car noise. In: Proc. of Int. Conf. on Acoust., Speech and Signal Processing, vol. 1, pp. 417–420 (1995)Google Scholar
  5. 5.
    Farooq, O., Datta, S.: Mel filter-like admissible wavelet packet structure for speech recognition. IEEE Signal Processing Letters 8, 196–198 (2001)CrossRefGoogle Scholar
  6. 6.
    Farooq, O.: Wavelet: a new tool for speech recognition. In: Proc. of the Int. Workshop on Technology Development in Indian Languages (2003)Google Scholar
  7. 7.
    Jin, H., Kubala, F., Schwartz, R.: Automatic Speaker Clustering. In: Proceedings of the Speech Recognition Workshop, pp. 108–111 (1997)Google Scholar
  8. 8.
    Kersta, L.G.: Voiceprint Identification. Nature 196, 1253–1257 (1962)CrossRefGoogle Scholar
  9. 9.
    Mallat, S.: A Wavelet Tour of Signal Processing, 2nd edn. Academic Press, London (1999)MATHGoogle Scholar
  10. 10.
    Mitra, S., Patil, H.A., Basu, T.K.: Polynomial classifier techniques for speaker recognition in Indian languages. In: Proc. National System Conference. IIT Kharagpur, pp. 304–308 (2003)Google Scholar
  11. 11.
    Sarikaya, R., Pellon, B.L., Hansen, J.H.L.: Wavelet packet transforms features with application to speaker identification. In: IEEE Nordic Signal Processing Symposium, pp. 81–84 (1998)Google Scholar
  12. 12.
    Sarikaya, R., Hansen, J.H.L.: High resolution speech feature parameterization for monophone based stressed speech recognition. IEEE Signal Processing Letters, 182–185 (2000)Google Scholar
  13. 13.
    Patil, H.A.: Speaker Recognition in Indian languages: A feature based approach. Ph.D. thesis, department of electrical engineering, IIT Kharagpur, India (July 2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Hemant A. Patil
    • 1
  • T. K. Basu
    • 2
  1. 1.Department of Electronics and Instrumentation EngineeringDr. B. C. Roy Engineering, CollegeDurgapurIndia
  2. 2.Department of Electrical EngineeringIndian Institute of Technology, IIT KharagpurIndia

Personalised recommendations