Particle Swarm Optimization for Feature Selection in Speaker Verification
The problem addressed in this paper concerns the feature subset selection for an automatic speaker verification system. An effective algorithm based on particle swarm optimization is proposed here for discovering the best feature combinations. After feature reduction phase, feature vectors are applied to a Gaussian mixture model which is a text-independent speaker verification model. The performance of proposed system is compared to the performance of a genetic algorithm-based system and the baseline algorithm. Experimentation is carried out, using TIMIT corpora. The results of experiments indicate that with the optimized feature subset, the performance of the system is improved. Moreover, the speed of verification is significantly increased since by use of PSO, number of features is reduced over 85% which consequently decrease the complexity of our ASV system.
KeywordsParticle Swarm optimization (PSO) Feature Selection (FS) Speaker Verification Gaussian Mixture Model (GMM) Genetic Algorithm (GA)
Unable to display preview. Download preview PDF.
- 1.Ganchev, T., Zervas, P., Fakotakis, N., Kokkinakis, G.: Benchmarking Feature Selection Techniques on the Speaker Verification Task. In: Fifth International Symposium on Communication Systems, Networks And Digital Signal Processing, pp. 314–318 (2006)Google Scholar
- 2.Bimbot, F., et al.: A Tutorial on Text-Independent Speaker Verification. EURASIP Journal on Applied Signal Processing 4, 430–451 (2004)Google Scholar
- 3.Jensen, R.: Combining rough and fuzzy sets for feature selection. Ph.D. Thesis, University of Edinburgh (2005)Google Scholar
- 4.Nemati, S., Boostani, R., Jazi, M.D.: A Novel Text-Independent Speaker Verification System Using Ant Colony Optimization Algorithm. In: Elmoataz, A., Lezoray, O., Nouboud, F., Mammass, D. (eds.) ICISP 2008. LNCS, vol. 5099, pp. 421–429. Springer, Heidelberg (2008)Google Scholar
- 8.Pandit, M., Kittkr, J.: Feature Selection for a DTW-Based Speaker Verification System, pp. 796–799. IEEE, Los Alamitos (1998)Google Scholar
- 9.Cohen, Zigel, Y.: On Feature Selection for Speaker Verification, of COST 275 workshop on The Advent of Biometrics on the Internet (2002)Google Scholar
- 13.Eberhart, R.C., Kennedy, J.: A new optimizer using particle swarm theory. In: Proceedings of the Sixth International Symposium on Micro Machine and Human Science, pp. 39–43 (1995)Google Scholar
- 15.Cheung-chi, L.: GMM-Based Speaker Recognition for Mobile Embedded Systems, Ph.D. Thesis, University of Hong Kong (2004)Google Scholar
- 17.Bins, J.: Feature Selection from Huge Feature Sets in the Context of Computer Vision. Ph.D. dissertation, Department Computer Science, Colorado State University (2000)Google Scholar
- 18.Garofolo, J., et al.: DARPA TIMIT Acoustic-Phonetic Continuous Speech Corpus CD-ROM. National Institute of Standards and Technology (1990)Google Scholar