Computer Science and Engineering

p-ISSN: 2163-1484     e-ISSN: 2163-1492

2011;  1(1): 22-25

doi: 10.5923/j.computer.20110101.04

Automatic Gender Identification Using Fusion of Generative and Discriminative Classifiers and Clustering of Spekaers from the Same Gender

Copyright © 2011 Scientific & Academic Publishing. All Rights Reserved.

Abstract

This paper proposes a two layer classifier fusion technique using clustering of training data from speakers of the same gender for automatic gender identification (AGI). The first layer is an acoustic classification layer for mapping MFCC and pitch acoustic feature space to score space. In this layer, a divisive clustering is proposed for dividing the speakers from each gender to some classes, where speakers in each class have similar vocal articulatory characteristics. Finally, the best structure could map 22 feature coefficients to 5 likelihood scores as new features. The second layer is a back-end classifier that receives the vectors of fused likelihood scores from the first layer. This means that the new feature coefficients are used in the second layer. GMM, SVM and MLP classifiers were evaluated in the middle and back-end layers. 96.53% gender classification accuracy was obtained on OGI multilingual corpus which is much better than the performance obtained by traditional AGI methods.

Keywords: Gender Identification, Classifier Fusion, Clustering, GMM, SVM, MLP

Paper's body in HTML will come soon.

Reference

[1]  H. Harb, and C. Liming, “Gender Identification using a General Audio Classifier,” in Multimedia and Expo, pp. II-733-6, 2003
[2]  W. H. Abdulla, and N. K. Kasabov, “Improving Speech Recognition Performance Through Gender Separation,” in Artificial Neural Networks and Expert Systems International Conference (ANNES), Dunedin, New Zealand, pp. 218-222, 2001
[3]  H. Harb, and L. Chen, “Voice-Based Gender Identification in Multimedia Applications,” Journal of Intelligent Information Systems, pp. 179-198, 2005
[4]  K.-H. Lee, S.-I. Kang, D.-H. Kim et al., “A Support Vector Machine-Based Gender Identification Using Speech Signal,” IEICE Transactions on Communications, pp. 3326-3329, 2008
[5]  J. Silovsky, and J. Nouza, “Speech, Speaker and Speaker's Gender Identification in Automatically Processed Broadcast Stream,” RADIOENGINEERING, pp. 42-48, 2006
[6]  Y. K. Muthusamy, R. A. Cole, and B. T. Oshika, “The OGI multilanguage telephone speech corpus,” pp. 895-898, 1992
[7]  T. Bocklet, A. Maier, J. G. Bauer et al., “Age and gender recognition for telephone applications based on GMM supervectors and support vector machines,” in, Institute of Electrical and Electronics Engineers Inc., Piscataway, NJ 08855-1331, United States, pp. 1605-1608, 2008
[8]  Y. Bo, E. Ambikairajah, and F. Chen, “Hierarchical Language Identification Based on Automatic Language Clustering,” in Interspeech, Antwerp, Belgium, pp. 178-181, 2007
[9]  M. A. Keyvanrad, and M. M. Homayounpour, “Feature Selection and Dimension Reduction for Automatic Gender Identification,” in 14th International CSI conference (CSICC2009), Tehran, Iran, pp., 2009