Text dependent speaker recognition using shifted MFCC

In the past decade, interest in using biometric technologies for person authentication in security systems has grown rapidly. Voice is one of the most promising and mature biometric modalities for secured access control. In this paper, we present a novel approach to recognize/identify speakers by including a new set of features and using Gaussian mixture models (GMMs). In this research, the concept of shifted MFCC is introduced so as to incorporate accent information in the recognition algorithm. The algorithm was evaluated using TIDIGIT dataset and the results showed improvements over the performance of our previous work [1].

[1]  Frank K. Soong,et al.  On the use of instantaneous and transitional spectral information in speaker recognition , 1988, IEEE Trans. Acoust. Speech Signal Process..

[2]  Douglas A. Reynolds,et al.  A Gaussian mixture modeling approach to text-independent speaker identification , 1992 .

[3]  Douglas A. Reynolds,et al.  Robust text-independent speaker identification using Gaussian mixture speaker models , 1995, IEEE Trans. Speech Audio Process..

[4]  Srikanth Mangayyagari.  Voice recognition system based on intra-modal fusion and accent classification , 2007 .

[5]  R. W. King,et al.  Automatic accent classification of foreign accented Australian English speech , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[6]  Dat Tran,et al.  A proposed likelihood transformation for speaker verification , 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

[7]  Michael Jessen,et al.  Forensic speaker verification using formant features and Gaussian mixture models , 2008, INTERSPEECH.