Speaker Verification Using Accumulative Vectors with Support Vector Machines

  • Manuel Aguado Martínez
  • Gabriel Hernández-Sierra
  • José Ramón Calvo de Lara
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8259)


The applications of Support Vector Machines (SVM) in speaker recognition are mainly related to Gaussian Mixtures and Universal Background Model based supervector paradigm. Recently, has been proposed a new approach that allows represent each acoustic frame in a binary discriminant space. Also a representation of a speaker - called accumulative vectors - obtained from the binary space has been proposed. In this article we show results obtained using SVM with the accumulative vectors and Nuisance Attribute Projection (NAP) as a method for compensating the session variability. We also introduce a new method to counteract the effects of the signal length in the conformation of the accumulative vectors to improve the performance of SVM.


speaker recognition binary values accumulative vectors Support Vector Machine Nuisance Attribute Projection 


  1. 1.
    Campbell, W., et al.: Support vector machines for speaker and language recognition. Computer Speech and Language 20, 210–229 (2006)CrossRefGoogle Scholar
  2. 2.
    Campbell, W., Sturim, D., Reynolds, D.: Support vector machines using GMM supervectors for speaker verification. IEEE Signal Processing Letters 13, 308–311 (2006)CrossRefGoogle Scholar
  3. 3.
    Anguera, X., Bonastre, J.F.: A novel speaker binary key derived from anchor models. In: Proc. Interspeech, pp. 2118–2121 (2010)Google Scholar
  4. 4.
    Hernández-Sierra, G., Bonastre, J.-F., Calvo de Lara, J.R.: Speaker recognition using a binary representation and specificities models. In: Alvarez, L., Mejail, M., Gomez, L., Jacobo, J. (eds.) CIARP 2012. LNCS, vol. 7441, pp. 732–739. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  5. 5.
    Solomonoff, A., Campbell, W.M., Boardman, I.: Advances in Channel Compensation for SVM speaker Recognition. In: Proc. Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), pp. 629–632 (2005)Google Scholar
  6. 6.
    Hautamaki, V., Kinnunen, T., Karkkainen, I., Tuononen, M., Saastamoinen, J., Franti, P.: Maximum a Posteriori estimation of the centroid model for speaker verification (2008)Google Scholar
  7. 7.
    Bonastre, J.F., Bousquet, P.M., Matrouf, D.: Discriminant binary data representation for speaker recognition. In: Proc. ICASSP, pp. 5284–5287 (2011)Google Scholar
  8. 8.
    Cristianini, N., Shawe-Taylor, J.: Support Vector Machines (2000)Google Scholar
  9. 9.
    Campbell, W., Sturim, D., Reynolds, D.: SVM based speaker verification using a GMM supervector kernel and NAP variability compensation. In: Proc. Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), pp. 637–640 (2005)Google Scholar
  10. 10.
    Dehak, N., et al.: Front-End Factor Analysis For Speaker Verification. IEEE Transactions on Audio, Speech and Language Processing 19(4), 788–798 (2010)CrossRefGoogle Scholar
  11. 11.
    Hatch, A.O., Kajarekar, S., Stolcke, A.: Within-Class Covariance Normalization for SVM-based Speaker Recognition. In: Proc. ICSLP, pp. 1471–1474 (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Manuel Aguado Martínez
    • 1
  • Gabriel Hernández-Sierra
    • 1
  • José Ramón Calvo de Lara
    • 1
  1. 1.Advanced Technologies Application CenterHavanaCuba

Personalised recommendations