A Supervised Text-Independent Speaker Recognition Approach

Authors: Tudor Barbu

Abstract:

We provide a supervised speech-independent voice recognition technique in this paper. In the feature extraction stage we propose a mel-cepstral based approach. Our feature vector classification method uses a special nonlinear metric, derived from the Hausdorff distance for sets, and a minimum mean distance classifier.

Keywords: Text-independent speaker recognition, mel cepstral analysis, speech feature vector, Hausdorff-based metric, supervised classification.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1331881

References:

[1] R. A. Cole, J. Mariani, H. Uszkoreit , A. Zaenen, V. Zue, Survey of the State of the Art in Human Language Technology. Cambridge University Press, 1997.
[2] T. Barbu, "Speech-dependent voice recognition system using a nonlinear metric", International Journal of Applied Mathematics, Volume 18, No. 4, 2005, pp. 501-514.
[3] H. Gish, M. Schmidt, "Text-Independent Speaker Identification", IEEE Signal Processing Magazine, IEEE,oct. 1994, pp. 1437-62.
[4] N. Bagge, C. Donica, "ELEC 301: Final Project Text Independent Speaker Recognition", ELEC 301 Signals and Systems Group Projects, 2001.
[5] D. A. Reynolds, R. C. Rose, "Robust text-independent speaker identification using Gaussian mixture speaker models", IEEE Trans. Speech Audio Processing, vol. 3, no. 1, 1995, pp. 72-83.
[6] T. Barbu, "Discrete speech recognition using a Hausdorff-based metric", In Proceedings of the 1st Int. Conference of E-Business and Telecommunication Networks, ICETE 2004, Setubal, Portugal, Vol. 3, Aug. 2004, pp.363-368.
[7] R. Duda, P. Hart, D. G. Stork, Pattern Classification, John Wiley & Sons, 2000.