Advertisement

Reduced Universal Background Model for Speech Recognition and Identification System

  • Lachachi Nour-Eddine
  • Adla Abdelkader
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7329)

Abstract

Minimal Enclosing Ball (MEB) has a limitation for dealing with a large dataset in which computational load drastically increases as training data size becomes large. To handle this problem in huge dataset used for speaker recognition and identification system, we propose two algorithms using Fuzzy C-Mean clustering method. Our method uses divide-and-conquer strategy; trains each decomposed sub-problems to get support vectors and retrains with the support vectors to find a global data description of a whole target class. Our study is experimented on Universal Background Model (UBM) architectures in speech recognition and identification system to eliminate all noise features and reducing time training. For this, the training data, learned by Support Vector Machines (SVMs), is partitioned among several data sources. Computation of such SVMs can be efficiently achieved by finding a core-set for the image of the data.

Keywords

Quadratique Programming (QP) Support Vector Machines (SVMs) Minimum Enclosing Ball (MEB) core- set kernel methods Fuzzy C-Mean 

References

  1. 1.
    Schölkopf, B., Smola, A.J.: Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. MIT Press, Cambridge (2001)Google Scholar
  2. 2.
    Kocsor, A., Kwork, J., Tsang, I.: Simpler core vector machines with enclosing balls. In: ICML 2007, pp. 911–918. ACM (2007)Google Scholar
  3. 3.
    Cheung, P.M., Kwok, J., Tsang, I.: Core vector machines: Fast SVM training on very large datasets. Journal of Machine Learning Research (6), 363–392 (2005)Google Scholar
  4. 4.
    Bãdoiu, M., Clarkson, K.L.: Optimal core-sets for balls. Computing Geometry Theory Application 1(40), 14–22 (2008)CrossRefGoogle Scholar
  5. 5.
    Vapnik, V.: The nature of statistical learning theory. Springer (1995)Google Scholar
  6. 6.
    Hsu, C., Lin, C.: A comparison of methods for multiclass support vector machines. IEEE Transactions on Neural Networks 13(2), 415–425 (2002)CrossRefGoogle Scholar
  7. 7.
    Crammer, K., Singer, Y.: On the algorithmic implementation of multiclass kernel-based vector machines. JMLR (2), 265–292 (2001)Google Scholar
  8. 8.
    Lee, Y., Li, Y., Wahba, G.: Multicategory support vector machines. Theory and application to the classification of microarray data and satellite radiance data. Journal of the American Statistical Association 99(465), 67–81 (2004)MathSciNetzbMATHCrossRefGoogle Scholar
  9. 9.
    Allende, H., Concha, C., Moraga, C., Nanculef, R.: Ad-svms: A light extension of SVMs for multicategory classification. International Journal of Hybrid Intelligent Systems 6(2), 69–79 (2009)zbMATHGoogle Scholar
  10. 10.
    Asharaf, S., Murty, M., Shevade, S.K.: Multiclass core vector machine. In: ICML 2007, pp. 41–48. ACM (2007)Google Scholar
  11. 11.
    Shawe-Taylor, J., Szedmak, S.: Multiclass learning at one-class complexity. Technical Report, no 1508, School of Electronics and Computer Science, Southampton, UK (2005)Google Scholar
  12. 12.
    Al-Zoubi, M.B., Hudaib, A., Al-Shboul, B.: A fast fuzzy clustering algorithm. In: Proceedings of the 6th WSEAS Int. Conf. on Artificial Intelligence, Knowledge Engineering and Data Bases, Corfu Island, Greece, pp. 28–32 (2007)Google Scholar
  13. 13.
    Jain, A.K., Dubes, R.C.: Algorithms for Clustering Data. Prentice Hall Inc., Englewood Cliffs (1988)zbMATHGoogle Scholar
  14. 14.
    Jain, A.K., Murty, M.N., Flynn, P.J.: Data Clustering - A review. ACM Computing Surveys 31(3) (September 1999)Google Scholar
  15. 15.
    Alkanhal, M., Alghamdi, M., Muzaffar, Z.: Speaker Verification based on Saudi Acceted Arabic Database. In: 9th International Symposium on Signal Processing and its Applications, ISSPA 2007, Sharjah, United Arab Emirate, pp. 1–4 (February 2007)Google Scholar
  16. 16.

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Lachachi Nour-Eddine
    • 1
  • Adla Abdelkader
    • 1
  1. 1.Computer Science DepartmentOran UniversityAlgeria

Personalised recommendations