Speaker Classification via Supervised Hierarchical Clustering Using ICA Mixture Model

详细信息    查看全文

• 关键词：Bounded Generalized Gaussian Mixture Model (BGGMM) ; Independent Component Analysis (ICA) ; Speaker classification ; Supervised hierarchical clustering ; ICA mixture model
• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：9680
• 期：1
• 页码：193-202
• 全文大小：338 KB
• 参考文献：1.Hansen, J., Hasan, T.: Speaker recognition by machines and humans: a tutorial review. Sig. Process. Mag. IEEE 32, 74–99 (2015)CrossRef
  2.Markowitz, J.: The many roles of speaker classification in speaker verification and identification. In: Mller, C. (ed.) Speaker Classification I. LNCS, vol. 4343, pp. 218–225. Springer, Berlin (2007)CrossRef
  3.Reynolds, D.A., Quatieri, T.F., Dunn, R.B.: Speaker verification using adapted gaussian mixture models. Digital Sig. Process. 10(1), 19–41 (2000)CrossRef
  4.Bourouis, S., Mashrgy, M.A., Bouguila, N.: Bayesian learning of finite generalized inverted Dirichlet mixtures: application to object classification and forgery detection. Expert Syst. Appl. 41, 2329–2336 (2014)CrossRef
  5.Bdiri, T., Bouguila, N., Ziou, D.: Visual scenes categorization using a flexible hierarchical mixture model supporting users ontology. In: 2013 IEEE 25th International Conference on Tools with Artificial Intelligence, pp. 262–267, Herndon, VA, USA, 4–6 Nov 2013
  6.Bdiri, T., Bouguila, N., Ziou, D.: Object clustering and recognition using multi-finite mixtures for semantic classes and hierarchy modeling. Expert Syst. Appl. 41, 1218–1235 (2014)CrossRef
  7.Azam, M., Bouguila, N.: Unsupervised keyword spotting using bounded generalized Gaussian mixture model with ICA. In: 2015 IEEE Global Conference on Signal and Information Processing (General Symposium), Orlando, USA (2015)
  8.Nguyen, P., Le, T., Tran, D., Huang, X., Sharma, D.: Fuzzy support vector machines for age and gender classification. In: INTERSPEECH, pp. 2806–2809 (2010)
  9.Vergin, R., Farhat, A., O’Shaughnessy, D.: Robust gender-dependent acoustic-phonetic modelling in continuous speech recognition based on a new automatic male/female classification. In: Fourth International Conference on Spoken Language, ICSLP 1996, Proceedings, vol. 2, pp. 1081–1084 (1996)
  10.Salazar, A.: ICA and ICAMM methods. In: On Statistical Pattern Recognition in Independent Component Analysis Mixture Modelling. Springer Theses, vol. 4, pp. 29–55. Springer, Berlin (2013)
  11.Lee, T.-W., Lewicki, M.S.: The generalized Gaussian mixture model using ICA. In: International Workshop on Independent Component Analysis, ICA 2000, pp. 239–244 (2000)
  12.Lee, T.-W., Lewicki, M.S., Sejnowski, T.J.: ICA mixture models for unsupervised classification with non-Gaussian sources and automatic context switching in blind signal separation. In: IEEE Transactions on Pattern Recognition and Machine Learning (2000)
  13.Lindblom, J., Samuelsson, J.: Bounded support Gaussian mixture modeling of speech spectra. IEEE Trans. Speech Audio Process. 11, 88–99 (2003)CrossRef
  14.Nguyen, T.M., Wu, Q.J., Zhang, H.: Bounded generalized Gaussian mixture model. Pattern Recogn. 47, 3132–3142 (2014)CrossRef
  15.Lee, T.-W., Lewicki, M.S.: Unsupervised image classification, segmentation, and enhancement using ICA mixture models. IEEE Trans. Image Process. 11(3), 270–279 (2002)CrossRef
  16.Garofolo, J.S., Lamel, L.F., Fisher, W.M., Fiscus, J.G., Pallett, D.S., Dahlgren, N.L.: DARPA TIMIT acoustic phonetic continuous speech corpus CDROM (1993). http://​www.​ldc.​upenn.​edu/​Catalog/​LDC93S1.​html
  17.Kabal, P.: TSP Speech Database. Technical report, Department of Electrical and Computer Engineering, McGill University, Montreal, Quebec, Canada (2002)
  
• 作者单位：Muhammad Azam (19)
  Nizar Bouguila (20)
  
  19. Department of Electrical and Computer Engineering, Concordia University, Montreal, QC, Canada
  20. Concordia Institute for Information Systems Engineering, Concordia University, Montreal, QC, Canada
  
• 丛书名：Image and Signal Processing
• ISBN：978-3-319-33618-3
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349
• 卷排序：9680

文摘

In this paper, speaker classification using supervised hierarchical clustering is provided. Bounded generalized Gaussian mixture model with ICA is adapted for statistical learning in the clustering framework. In the presented framework ICA mixture model is learned through training data and the posterior probability is used to split the training data into clusters. The class label of the training data is further selected to mark each cluster into a specific class. The cluster-class information from the training process is taken as reference for the classification of test data into different speaker classes. This framework is employed for the gender and 10 speakers classification and TIMIT and TSP speech corpora are selected to validate and test the classification framework. This classification framework also validate the statistical learning of our recently proposed ICA mixture model. In order to examine the performance of the ICA mixture model, the classification results are compared with same framework using Gaussian mixture model. It is observed that: (i) presented clustering framework performs well for the speaker classification, (ii) ICA mixture model outperforms Gaussian mixture model in the statistical learning based on the classification accuracy for gender and multi-class scenarios.