Speaker Discrimination Using Several Classifiers and a Relativistic Speaker Characterization

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9680)

Abstract

Automatic Speaker Discrimination consists in checking whether two speech signals belong to the same speaker or not. It is often difficult to decide what could be the best classifier to use in some specific circumstances. That is why, we implemented nine different classifiers, namely: Linear Discriminant Analysis, Adaboost, Support Vector Machines, Multi-Layer Perceptron, Linear Regression, Generalized Linear Model, Self Organizing Map, Second Order Statistical Measures and Gaussian Mixture Models. Moreover, a special feature reduction was proposed, which we called Relativistic Speaker Characteristic (RSC). On the other hand we further intensified the feature reduction by adding a second step of feature transformation using a Principal Component Analysis (PCA). Experiments of speaker discrimination are conducted on Hub4 Broadcast-News. Results show that the best classifier is the SVM and that the proposed feature reduction association (RSC-PCA) is extremely efficient in automatic speaker discrimination.

Keywords

Speaker discrimination Speaker verification Relativistic speaker characteristic PCA reduction Classification models 

References

  1. 1.
    Rose, P.: Forensic speaker discrimination with Australian English vowel acoustics. In: ICPhS, XVI (2007)Google Scholar
  2. 2.
    Matrouf, D., Bonastre, J.F.: Accurate log-likelihood ratio estimation by using test statistical model for speaker verification. In: The Speaker and Language Recognition Workshop, Odyssey (2006)Google Scholar
  3. 3.
    Meignier, S., et al.: Step- by- step and integrated approaches in broadcast news speaker diarization. Comput. Speech Lang. 20, 303–330 (2006)CrossRefGoogle Scholar
  4. 4.
    Meignier, S.: Indexation en locuteurs de documents sonores: segmentation d’un document et Appariement d’une collection. Ph.D. thesis, LIA Avignon, France (2002)Google Scholar
  5. 5.
    Ouamour, S., Guerti, M., Sayoud, H.: A new relativistic vision in speaker discrimination. Can. Acoust. J. 36(4), 24–34 (2008). ISSN 0711-6659Google Scholar
  6. 6.
    Li, M., Xing, Y., Luo, R.: Hierarchical speaker verification based on PCA and kernel fisher discriminant. In : 4th International Conference on Natural Computation, pp. 152–156 (2008)Google Scholar
  7. 7.
    Zhao, Z.D., Zhang, J., Tian, J.F., Lou, Y.Y.: An effective identification method for speaker recognition based on PCA and double VQ. In: Proceedings of the Eighth International Conference on Machine Learning and Cybernetics, Baoding, pp. 1686–1689 (2009)Google Scholar
  8. 8.
    Jayakurnar, A., Vimal Krishnan, V.R., BabuAnto, P.: Text dependent speaker recognition using discrete stationary wavelet transform and PCA. In: International Conference on the Current Trends in Information Technology CTIT, pp. 1–4 (2009)Google Scholar
  9. 9.
    Zhou, Y., Zhang, X., Wang, J., Gong, Y.: Research on speaker feature dimension reduction based on CCA and PCA. In: International Conference on Wireless Communications and Signal Processing (WCSP), pp. 1–4 (2010)Google Scholar
  10. 10.
    Xiao-chun, L., Jun-xun, Y., A.: Text-independent speaker recognition system based on probabilistic principle component analysis. In: 3rd International Conference on System Science, Engineering Design and Manufacturing Informatization, pp. 255–260 (2012)Google Scholar
  11. 11.
    Contributors of Wikipedia: Linear discriminant analysis. https://en.wikipedia.org/wiki/Linear_discriminant_analysis. Accessed Nov 2015
  12. 12.
    Contributors of Wikipedia: Adaboost. https://en.wikipedia.org/wiki/AdaBoost. Accessed Nov 2015
  13. 13.
    Contributors of Wikipedia: Support vector machine. https://en.wikipedia.org/wiki/Support_vector_machine. Accessed Nov 2015
  14. 14.
    Sayoud, H.: Automatic speaker recognition – connexionnist approach. Ph.D. thesis, USTHB University, Algiers (2003)Google Scholar
  15. 15.
    Contributors of Wikipedia: linear discriminant analysis. https://en.wikipedia. Last Accessed Nov 2015, Wikipedia, “Linear regression”. http://en.wikipedia.org/wiki/Linear_regression. From Wikipedia, Last Accessed 28 Mar 2013
  16. 16.
    Huang, X., Pan, W.: Linear regression and two-class classification with gene expression data. Bioinformatics 19(16), 2072–2078 (2003)CrossRefGoogle Scholar
  17. 17.
    Contributors of Wikipedia, 2015. Generalized linear model. Last Accessed Nov 2015. https://en.wikipedia.org/wiki/Generalized_linear_model
  18. 18.
    Kohonen, T.: The self-organizing map. Proc. IEEE 78(9), 1464–1480 (1990). doi: 10.1109/5.58325. Invited PaperCrossRefGoogle Scholar
  19. 19.
    Tambouratzis, G., Hairetakis, G., Markantonatou, S., Carayannis, G.: Applying the SOM Model to Text Classification According to Register and Stylistic Content. Int. J. Neural Syst. 13(1), 1–11 (2003)CrossRefGoogle Scholar
  20. 20.
    Bimbot, F., Magrin-Chagnolleau, I., Mathan, L.: Second-Order Statistical Measures for text-independent Broadcaster Identification. Speech Commun. 17(1–2), 177–192 (1995)CrossRefGoogle Scholar
  21. 21.
    Reynolds, D.A.: Speaker identification and verification using Gaussian mixture speaker models. Speech Commun. 17(1–2), 91–108 (1995)CrossRefGoogle Scholar
  22. 22.
    Shlens, J.: A tutorial on principal component analysis - Derivation, Discussion and Singular Value Decomposition. Version 1, (2003). www.cs.princeton.edu/picasso/mats/PCA-Tutorial-Intuition_jp.pdf

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.USTHB UniversityAlgiersAlgeria

Personalised recommendations