Speaker Verification in Noisy Environment Using Missing Feature Approach

  • Dayana Ribas
  • Jesús A. Villalba
  • Eduardo Lleida
  • José R. Calvo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6419)


In order to handle speech signals corrupted by noise in speaker verification and provide robustness to systems, this paper evaluates the use of missing feature (MF) approach with a novel combination of techniques. A mask estimation based on spectral subtraction is used to determine the reliability of spectral components in a speech signal corrupted by noise. A cluster based reconstruction technique is used to remake the damaged spectrum. The verification performance was evaluated through a speaker verification experiment with signals corrupted by white noise under different signal to noise ratios. The results were promising since they reflected a relevant increase of speaker verification performance, applying MF approach with this combination of techniques.


Noisy Environment Equal Error Rate Speaker Recognition Speaker Verification Spectral Subtraction 
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.


  1. [1]
    Benesty, J., Chen, J., Huang, Y., Cohen, I.: Noise Reduction in Speech Processing. Springer Topics in Signal Processing 2 (2009)Google Scholar
  2. [2]
    Raj, B., Stern, R.: Missing-Feature Approaches in Speech Recognition. In: IEEE Signal Proc. Magazine (2005)Google Scholar
  3. [3]
    Padilla, M., Quatieri, T., Reynolds, D.: MF Theory with Soft Spectral Subtraction for Speaker Verification (2006)Google Scholar
  4. [4]
    Ming, J., Hazen, T., Glass, J.R., Reynolds, D.A.: Robust Speaker Recognition in Noisy Conditions. IEEE Trans. on Speech and Audio Proc. 15, 1711–1723 (2007)CrossRefGoogle Scholar
  5. [5]
    Pullella, D., Kuhne, M., Togneri, R.: Robust Speaker Identification Using Combined Feature Selection and Missing Data Recognition. In: ICASSP (2008)Google Scholar
  6. [6]
    Kuhne, M., Pullella, D., Togneri, R., Nordholm, S.: Towards the use of full covariance models for missing data speaker recognition. In: ICASSP (2008)Google Scholar
  7. [7]
    Cerisara, C., Demange, S., Haton, J.-P.: On noise masking for automatic missing data speech recognition: a survey and discussion. Computer Speech and Language 21(3), 443–457 (2007)CrossRefGoogle Scholar
  8. [8]
    Drygajlo, A., El-Maliki, M.: Speaker Verification in Noisy Enviroments with Combined Spectral Subtraction and MF Theory. In: Signal Proc. Laboratory, Swiss Federal Institute of Technology at Lausanne (1998)Google Scholar
  9. [9]
    Pelecanos, J., Sridharan, S.: Feature warping for robust speaker verification. Speaker Odyssey (2001)Google Scholar
  10. [10]
    Raj, B., Seltzer, M., Stern, R.M.: Reconstruction of MFs for robust speech recognition. Speech Communication 43 (2004)Google Scholar
  11. [11]
    Seltzer, M., Raj, B., Stern, R.M.: A Bayesian classifier for spectrographic mask estimation for MF speech recognition. Speech Communication 43 (2004)Google Scholar
  12. [12]
    Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society (1977)Google Scholar
  13. [13]
    The NIST year, speaker recognition evaluation plan (2006),
  14. [14]
    Berouti, M., Schwartz, R., Makhoul, J.: Enhancement of speech corrupted by acoustic noise. In: IEEE ICASSP (1979)Google Scholar
  15. [15]
    Martin, R.: Noise Power Spectral Density Estimation Based on Optimal Smoothing and Minimum Statistics. IEEE Trans. on Speech and Audio Proc. 9 (2001)Google Scholar
  16. [16]
    Reynolds, D., Quatieri, T., Dunn, R.: Speaker Verification Using Adapted Gaussian Mixture Models. Digital Signal Proc. 10 (2000)Google Scholar
  17. [17]
    Bilmes, J.: Graphical Models and Automatic Speech Recognition. Mathematical Foundations of Speech and Language Proc., 191–235 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Dayana Ribas
    • 1
  • Jesús A. Villalba
    • 2
  • Eduardo Lleida
    • 2
  • José R. Calvo
    • 1
  1. 1.Advanced Technologies Application Center (CENATAV)PlayaCuba
  2. 2.Communications Technology Group (GTC), Aragon Institute for Engineering Research (I3A)University of ZaragozaSpain

Personalised recommendations