A Novel Text-Independent Speaker Verification System Using Ant Colony Optimization Algorithm

Automatic speaker verification (ASV) has become increasingly desirable in recent years. This system in general, requires 20 to 40 features as input for satisfactory verification. In this paper, features size is reduced by Ant Colony Optimization (ACO) technique to increase the ASV performance. After feature reduction phase, feature vectors are applied to a Gaussian Mixture Model (GMM) which is a text-independent speaker verification Model. Experiments are conducted on a subset of TIMIT corpora. The results indicate that with the optimized feature set, the performance of the ASV system is improved. Moreover, the speed of verification is significantly increased because number of features is reduced over 73% which consequently decrease the complexity of our ASV system.

[1]  Toby Berger,et al.  Efficient text-independent speaker verification with structural Gaussian mixture models and neural network , 2003, IEEE Trans. Speech Audio Process..

[2]  Rita H. Wouhaybi,et al.  Comparison of neural networks for speaker recognition , 1999, ICECS'99. Proceedings of ICECS '99. 6th IEEE International Conference on Electronics, Circuits and Systems (Cat. No.99EX357).

[3]  Josef Kittler,et al.  Feature selection for a DTW-based speaker verification system , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[4]  Robert M. Gray,et al.  An Algorithm for Vector Quantizer Design , 1980, IEEE Trans. Commun..

[5]  Richard Jensen,et al.  Combining rough and fuzzy sets for feature selection , 2004 .

[6]  Ivan Magrin-Chagnolleau,et al.  Second-order statistical measures for text-independent speaker identification , 1995, Speech Commun..

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

[8]  Qin Jin,et al.  Phonetic speaker recognition using maximum-likelihood binary-decision tree models , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[9]  G. Di Caro,et al.  Ant colony optimization: a new meta-heuristic , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[10]  Karim Faez,et al.  Face Recognition System Using Ant Colony Optimization-Based Selected Features , 2007, 2007 IEEE Symposium on Computational Intelligence in Security and Defense Applications.

[11]  Jr. J.P. Campbell,et al.  Speaker recognition: a tutorial , 1997, Proc. IEEE.

[12]  J. Picone,et al.  Speaker Verification using Support Vector Machines , 2006, Proceedings of the IEEE SoutheastCon 2006.

[13]  Cheung-Chi Leung.  GMM-based speaker recognition for mobile embedded systems , 2004 .

[14]  Jonathan G. Fiscus,et al.  Darpa Timit Acoustic-Phonetic Continuous Speech Corpus CD-ROM {TIMIT} | NIST , 1993 .

[15]  Asoke K. Nandi,et al.  Robust Text-Independent Speaker Verification Using Genetic Programming , 2007, IEEE Transactions on Audio, Speech, and Language Processing.