We propose an effective feature extraction technique for obtaining essential time-frequency information from the linear prediction (LP) residual signal, which are closely related to the glottal vibration of individual speaker. With pitch synchronous analysis, wavelet transform is applied to every two pitch cycles of the LP residual signal to generate a new feature vector, called Wavelet Based Feature extraction (WBFE), which provides additional speaker discriminative power to the commonly used linear predictive Cepstral coefficients (LPC).WBFE out performs the LPCs coefficients. In this paper, we have demonstrated the effectiveness of using vocal source features to supplement vocal tract features for improved speaker verification and the verification results are displayed in the MATLAB.

1. G.Chenchamma “Speech Coding with Linear Predictive Coding,” Proceedings of the ICMEE2009, Chennai, India was published in www.worldscibooks.com/etextbook.
2. Makhoul, J., “Linear Prediction: A Tutorial Review,”Proceedings of the IEEE, Vol. 63, pp. 561-579, 1975.
3. Furui, S., “Cepstral Analysis Technique for AutomaticSpeaker Verification,” IEEE Trans. Acoust.,Speech, Signal Processing, Vol. ASSP-29, pp. 254-272, 1981.Tavel, P. 2007 Modeling and Simulation Design. AK Peters Ltd.
4. Campbell, J. P., “Speaker Recognition: A Tutorial,”Proceedings of the IEEE, Vol. 85, No. 9, pp. 1437-1462, 1997.
5. Sonmez, K., Shriberg, E., Heck, L., and Weintraub,M., “Modeling Dynamic Prosodic variation for Speaker Verification,” Proc. ICSLP 1998, Sydney,pp. 3189-3192..
6. Thevenaz, P., and Hugli, H., “Usefulness of theLPC Residue in Text-independent Speaker Verification,”Speech Communication, Vol. 17, pp. 145-157,1995.
7. Plumpe, M. D., Quatieri, T. F., and Reynolds, D. A.,“Modeling of the Glottal Flow erivative Waveformwith Application to Speaker Identification,”IEEE Trans. Speech Audio Processing, Vol. 7, No.5, pp. 569-585, 1999.
8. ZhengNengheng, and Ching, P.C., “Using HaarTransformed Vocal Source Information for AutomaticSpeaker Recognition,” to appear in the Proc.ICASSP2004, Montreal, Canada
9. Quatieri, T. F., Discrete-Time Speech Signal Processing, Prentice-Hall, 2001
10. Noll, A. M., “Cestrum Pitch Determination,” J.Acoust. Soc. Am., Vol. 41, pp. 293-309, 1967.
11. Reynolds, D. A., “Speaker Identification and Verification Using Gaussian Mixture Speaker Models,”Speech Communication, Vol. 17, pp. 91-108, 1995.
12. Higgins, A., Bahler, L., and Porter, J., “Speaker Verification Using Randomized Phrase Prompting,”Digital Signal Processing, Vol. 1, pp.89-106. 1991.

LP residual WBFE LPC