An improved ant colony optimization algorithm and its application to text-independent speaker verification system

• Autorzy: Aghdam M. H.
• Języki publikacji: EN

Abstrakty

EN

With the growing trend toward remote security verification procedures for telephone banking, biometric security measures and similar applications, automatic speaker verification (ASV) has received a lot of attention in recent years. The complexity of ASV system and its verification time depends on the number of feature vectors, their dimensionality, the complexity of the speaker models and the number of speakers. In this paper, we concentrate on optimizing dimensionality of feature space by selecting relevant features. At present there are several methods for feature selection in ASV systems. To improve performance of ASV system we present another method that is based on ant colony optimization (ACO) algorithm. After feature selection phase, feature vectors are applied to a Gaussian mixture model universal background model (GMM-UBM) which is a text-independent speaker verification model. The performance of proposed algorithm is compared to the performance of genetic algorithm on the task of feature selection in TIMIT corpora. The results of experiments indicate that with the optimized feature set, the performance of the ASV system is improved. Moreover, the speed of verification is significantly increased since by use of ACO, number of features is reduced over 80% which consequently decrease the complexity of our ASV system.

Słowa kluczowe

EN

ant colony; optimization; ant colony optimization; ACO; security; automatic speaker verification; ASV; feature space; Gaussian mixture model universal background model; GMM-UBM

• Wydawca: University of Social Sciences
• Czasopismo: Journal of Artificial Intelligence and Soft Computing Research
• Rocznik: 2012
• Tom: Vol. 2, No. 4
• Strony: 301--315
• Opis fizyczny: Bibliogr. 45 poz., rys.

Twórcy

autor

Aghdam M. H.

• Department of Computer Engineering and Information Technology, Payam Noor University PO BOX 19395-3697, Tehran, IRAN

Bibliografia

• [1] B. Xiang, and T. Berger, Efficient Text-Independent Speaker Verification with Structural Gaussian Mixture Models and Neural Network. IEEE Transactions on Speech and Audio Processing, 11(5), 2003.
• [2] I. Lapidot, H. Guterman, and A. Cohen, Unsupervised speaker recognition based on competition between self-organizing maps. IEEE Transactions on Neural Networks, 13(2), 2002, 877–887.
• [3] A. Martin, and M. Przybocki, Speaker recognition in a multi-speaker environment. Proc. of 7th European Conf. Speech Communication and Technology, CityplaceAalborg, countryregionDenmark, 2001, 787–790.
• [4] P. Day, and A.K. Nandi, Robust Text-Independent Speaker Verification Using Genetic Programming. IEEE Transactions on Audio, Speech, and Language Processing, 15(1), 2007, 285-295.
• [5] R. Jensen, Combining rough and fuzzy sets for feature selection. Ph.D. thesis, PlaceTypeplaceUniversity of PlaceNameEdinburgh, 2005.
• [6] S. Nemati, R. Boostani, and M.D. Jazi, A Novel Text-Independent Speaker Verification System using Ant Colony Optimization Algorithm. Proc. Internat. Conf. on Image and Signal Processing ICISP2008, LNCS 5099, Springer-Verlag, Berlin Heidelberg, 2008, 421–429.
• [7] H.R. Kanan, K. Faez, and M. Hosseinzadeh Aghdam, Face Recognition System Using Ant Colony Optimization-Based Selected Features. Proc. of the First IEEE Symposium on Computational Intelligence in Security and Defense Applications (CISDA), placecountry-regionUSA, 2007, 57-62.
• [8] M. Hosseinzadeh Aghdam, N. Ghasem-aghaee, and M.E. Basiri, Application of Ant Colony Optimization for Feature Selection in Text Categorization. Proc. of the IEEE Congress on Evolutionary Computation, 2008.
• [9] M. Pandit, and J. Kittkr, Feature Selection for a DTW-Based Speaker Verification System. Proc. of the 1998 IEEE Internat. Conf. on Acoustics,Speech and Signal Processing, CitySeattle, WA, placecountry-regionUSA, 1998, 769-772.
• [10] A. Cohen, and Y. Zigel, On Feature Selection for Speaker Verification. Proc. of COST 275 workshop on The Advent of Biometrics on the Internet, 2002, 89–92.
• [11] T. Ganchev, P. Zervas, N. Fakotakis, and G. Kokkinakis, Benchmarking Feature Selection Techniques on the Speaker Verification Task, 2006.
• [12] M. Srinivas, and L.M. Patnik, Genetic Algorithms: A Survey. IEEE Computer Society Press, Los lamitos, 1994.
• [13] A. Haydar, M. Demirekler, and M.K. Yurtseven, Feature selection using genetic algorithm and its application to speaker verification, Electron. Lett., vol. 34, no. 15,( July 1998), 1457–1459.
• [14] M. Dorigo, and G.D. Caro, Ant Colony Optimization: A New Meta-heuristic. Proc. of the Congress on Evolutionary Computing, 1999.
• [15] M. Dorigo, V. Maniezzo, and A. Colorni, Ant System: Optimization by a colony of cooperating agents. IEEE Transaction on Systems, Man, and Cybernetics-Part B, 26(1), 1996, 29–41.
• [16] V. Maniezzo, and A. Colorni, the Ant System Applied to the Quadratic Assignment Problem. IEEE Transaction on Knowledge and Data Engineering, 11(5), 1999, 769–778.
• [17] F. Bimbot, J.F. Bonastre, C. Fredouille, G. Gravier, I. Magrin-Chagnolleau, S. Meignier, T. Merlin, J. Ortega-Garcia, D. Petrovska-Delacretaz, and D.A. Reynolds, A tutorial on textindependent speaker verification. Eurasip Journal on Applied Signal Processing, 2004, 430-451.
• [18] M.E. Basiri, N. Ghasem-Aghaee, and M.H. Aghdam, Using ant colony optimization-based selected features for predicting post-synaptic activity in proteins. Proc. of 6th European Conf. on Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics, LNCS 4973, Springer-Verlag Berlin Heidelberg, 2008, 12–23.
• [19] L. Cheung-chi, GMM-Based Speaker Recognition for placeMobile Embedded Systems. Ph.D. thesis, placePlaceTypeUniversity of PlaceName-Hong Kong, 2004.
• [20] D.A. Reynolds, and R.C. Rose, Robust textindependent speaker identification using Gaussian mixture speaker models. IEEE Transactions on Speech and Audio Processing, 3(1), 1995, 72- 83.
• [21] D.A. Reynolds, T.F. Quatieri, and R.B. Dunn, Speaker verification using adapted Gaussian mixture models. Digital Signal Processing, 10, 2000, 19–41.
• [22] D. Neiberg, Text Independent speaker verification using adapted Gaussian mixture models. Ph.D. thesis, Centre for Speech Technology (CTT) Department of Speech, Music and Hearing KTH, Stockholm, Sweden, 2001.
• [23] Y. Linde, A. Buzo, and R. Gray, An Algorithm for Vector Quantizer Design. IEEE Transactions on Communications, 28(1), 1980, 84-95.
• [24] J. Navratil, Q. Jin, W.D. Andrews, & J.P. Campbell, Phonetic speaker recognition using maximum-likelihood binary-decision tree models. Proc. IEEE Internat. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), place-Hong Kong, 2003.
• [25] V. Wan, Speaker Verification Using Support Vector Machines. Ph.D. thesis, University Sheffield, U.K, 2003.
• [26] R. Wouhaybi, and M.A. Al-Alaou, Comparison of neural networks for speaker recognition. Proc. 6th IEEE Internat. Conf. on Electronics, Circuits Systems (ICECS), 1999, 125-128.
• [27] D. Mladeni, Feature Selection for Dimensionality Reduction. Subspace, Latent Structure and Feature Selection, Statistical and Optimization, PerspectivesWorkshop, SLSFS 2005, Bohinj, Slovenia, LNCS 3940 Springer, 2006, 84–102.
• [28] R.O. Duda, and P.E. Hart, Pattern Classification and Scene Analysis. John Wiley & Sons, placeChichester, 1973.
• [29] X.Wang, J. Yang, X. Teng,W. Xia, and R. Jensen, Feature selection based on rough sets and particle swarm optimization. Pattern Recognition Letters, 28(4), 2007, 459–471.
• [30] A.A. Ani, Ant Colony Optimization for Feature Subset Selection. Transaction on Engineering, Computing and Technology, 4, 2005, 35–38.
• [31] C.K. Zhang, and H. Hu, Feature Selection Using the Hybrid of Ant Colony Optimization and Mutual Information for the Forecaster. Proc. of the 4th Internat. Conf. on Machine Learning and Cybernetics, 2005, 1728–1732.
• [32] J. Bins, Feature Selection from Huge Feature Sets in the Context of Computer Vision. Ph.D. Thesis, Department Computer Science, PlaceNameplaceColorado PlaceTypeState PlaceTypeUniversity, 2000.
• [33] M. Dorigo, and C. Blum, Ant colony optimization theory: A survey. Theoretical Computer Science, 2005, 243–278.
• [34] M. Dorigo, Optimization, Learning and Natural Algorithms. Ph.D. thesis, Dipartimento di Electtronica, Politecnico di Milano. Italy, 1992.
• [35] L.M. Gambardella, and M. Dorigo, Ant-Q: A Reinforcement Learning Approach to the TSP. Proc. of the Twelfth Internat. Conf. on Machine Learning, 1995, 252–260.
• [36] T. Sttzle, and H.H. Hoos, MAX-MIN Ant System and Local Search for the Traveling Salesman Problem. Proc. of IEEE Internat. Conf. on Evolutionary Computation, 1997, 309–314.
• [37] R. Montemanni, L.M. Gambardella, A.E. Rizzoli, and A.V. Donati, A new algorithm for a Dynamic Vehicle Routing Problem based on Ant Colony System. Istituto Dalle Molle Di Studi Sull Intelligenza Artificiale, Technical Report IDSIA-23-02,
• [38] C. Blum, and M. Dorigo, The hyper-cube framework for ant colony optimization. IEEE Transaction on Systems, Man, and Cybernetics -Part B, 34(2), 2004, 1161–1172.
• [39] G. Leguizamon, and Z. Michalewicz, A New Version of Ant System for Subset Problems. Proc. of IEEE Congress on Evolutionary Computation 1999.
• [40] Z. Pawlak, Rough Sets: Theoretical Aspects of Reasoning about Data. Kluwer Academic Publishing, placeCityDordrecht, 1991.
• [41] J. Yang, and V. Honavar, Feature Subset Selection Using a Genetic Algorithm. IEEE Intelligent Systems. 13, 1998, 44–49.
• [42] W.F. Punch, E.D. Goodman, L.C.S.M. Pei, P. Hovland, and R. Enbody, Further research on Feature Selection and Classification using Genetic Algorithms. Proc. Internat. Conf. on Genetic Algorithms, 1993, 557–564.
• [43] M. Raymer, W. Punch, E. Goodman, L. Kuhn, and A.K. Jain, Dimensionality Reduction Using Genetic Algorithms. IEEE Transactions on Evolutionary Computing, 4, 2000, 164–171.
• [44] J. Garofolo, et al. DARPA TIMIT Acoustic-Phonetic Continuous Speech Corpus CD-ROM. National PlaceTypeplaceInstitute of PlaceName- Standards and Technology, 1990.
• [45] A. Martin, G. Doddington, T. Kamm, M. Ordowski, and M. Przybocki, the DET Curve in Assessment of Detection Task Performance. Proc. Eurospeech, 4, 1997, 1895–1898.