Advertisement

Identify the Benefits of the Different Steps in an i-Vector Based Speaker Verification System

  • Pierre-Michel Bousquet
  • Jean-François Bonastre
  • Driss Matrouf
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8259)

Abstract

This paper focuses on the analysis of the i-vector paradigm, a compact representation of spoken utterances that is used by most of the state of the art speaker verification systems. This work was mainly motivated by the need to quantify the impact of their steps on the final performance, especially their ability to model data according to a theoretical Gaussian framework. These investigations allow to highlight the key points of the approach, in particular a core conditioning procedure, that lead to the success of the i-vector paradigm.

Keywords

Linear Discriminant Analysis Conditioning Procedure Equal Error Rate Speaker Recognition Speech Utterance 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Dehak, N., Kenny, P., Dehak, R., Dumouchel, P., Ouellet, P.: Front-End Factor Analysis for Speaker Verification. IEEE Transactions on Audio, Speech, and Language Processing 19, 788–798 (2011)CrossRefGoogle Scholar
  2. 2.
    Reynolds, D.A.: A Gaussian mixture modeling approach to text-independent speaker identification. PhD thesis, Georgia Institute of Technology (1992)Google Scholar
  3. 3.
    Dehak, N., Dehak, R., Kenny, P., Brummer, N., Ouellet, P., Dumouchel, P.: Support Vector Machines versus Fast Scoring in the Low-Dimensional Total Variability Space for Speaker Verification. In: International Conference on Speech Communication and Technology, pp. 1559–1562 (2009)Google Scholar
  4. 4.
    Hatch, A.O., Kajarekar, S., Stolcke, A.: Within-Class Covariance Normalization for SVM-based Speaker Recognition. In: International Conference on Speech Communication and Technology, pp. 1471–1474 (2006)Google Scholar
  5. 5.
    Kenny, P.: Bayesian speaker verification with heavy-tailed priors. In: Speaker and Language Recognition Workshop, IEEE Odyssey (2010)Google Scholar
  6. 6.
    Prince, S.J., Elder, J.H.: Probabilistic linear discriminant analysis for inferences about identity. In: IEEE International Conference on Computer Vision, pp. 1–8 (2007)Google Scholar
  7. 7.
    Bousquet, P.M., Larcher, A., Matrouf, D., Bonastre, J.F., Plchot, O.: Variance-Spectra based Normalization for I-vector Standard and Probabilistic Linear Discriminant Analysis. In: Speaker and Language Recognition Workshop, IEEE Odyssey (2012)Google Scholar
  8. 8.
    Bousquet, P.M., Matrouf, D., Bonastre, J.F.: Intersession compensation and scoring methods in the i-vectors space for speaker recognition. In: International Conference on Speech Communication and Technology, pp. 485–488 (2011)Google Scholar
  9. 9.
    Garcia-Romero, D., Espy-Wilson, C.Y.: Analysis of i-vector length normalization in speaker recognition systems. In: International Conference on Speech Communication and Technology, pp. 249–252 (2011)Google Scholar
  10. 10.
    Brummer, N., de Villiers, E.: The speaker partitioning problem. In: Speaker and Language Recognition Workshop, IEEE Odyssey (2010)Google Scholar
  11. 11.
    Campbell, W.M., Sturim, D., Borgstrom, B.J., Dunn, R., McCree, A., Quatieri, T.F., Reynolds, D.A.: Exploring the impact of advanced front-end processing on nist speaker recognition microphone tasks. In: Speaker and Language Recognition Workshop, IEEE Odyssey (2012)Google Scholar
  12. 12.
    Bonastre, J.F., Bousquet, P.M., Matrouf, D., Anguera, X.: Discriminant binary data representation for speaker recognition. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP, pp. 5284–5287 (2011)Google Scholar
  13. 13.
    Bonastre, J.F., Anguera, X., Sierra, G.H., Bousquet, P.M.: Speaker modeling using local binary decisions. In: International Conference on Speech Communication and Technology, pp. 485–488 (2011)Google Scholar
  14. 14.
    Kenny, P.: A small footprint i-vector extractor. In: Speaker and Language Recognition Workshop, IEEE Odyssey (2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Pierre-Michel Bousquet
    • 1
  • Jean-François Bonastre
    • 1
  • Driss Matrouf
    • 1
  1. 1.LIAUniversity of AvignonFrance

Personalised recommendations