Advertisement

Channel / Handset Mismatch Evaluation in a Biometric Speaker Verification Using Shifted Delta Cepstral Features

  • José R. Calvo
  • Rafael Fernández
  • Gabriel Hernández
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4756)

Abstract

This paper examines the application of Shifted Delta Cepstral (SDC) features in biometric speaker verification and evaluates its robustness to channel/handset mismatch due by telephone handset variability. SDC features were reported to produce superior performance to delta features in cepstral feature based Language Identification systems. The result of the experiment reflects superior performance of SDC features regarding to delta features in biometric speaker verification using speech samples from Ahumada Spanish database.

Keywords

biometrics speaker verification cepstral features shifted delta cepstral features channel mismatch 

References

  1. 1.
    Ratha, N.K., Senior, A., Bolle, R.M.: Automated Biometrics. In: Singh, S., Murshed, N., Kropatsch, W.G. (eds.) ICAPR 2001. LNCS, vol. 2013, pp. 445–474. Springer, Heidelberg (2001)Google Scholar
  2. 2.
    Ortega-Garcia, J., Bigun, J., Reynolds, D., Gonzalez-Rodriguez, J.: Authentication gets personal with biometrics. IEEE Signal Processing Magazine 50–62 (2004)Google Scholar
  3. 3.
    Heck, L.P., Konig, Y., Sonmez, M.K., Weintraub, M.: Robustness to telephone handset distortion in speaker recognition by discriminative feature design. Speech Communication 31, 181–192 (2000)CrossRefGoogle Scholar
  4. 4.
    Mammone, R., Zhang, X., Ramachandran, R.: Robust speaker recognition. IEEE Signal Processing Magazine 58–71 (1996)Google Scholar
  5. 5.
    Rahim, M.G., Juang, B.H.: Signal Bias Removal by Maximum Likelihood Estimation for Robust Telephone Speech Recognition. IEEE Trans. On Speech and Audio Processing 4(1), 19–30 (1996)CrossRefGoogle Scholar
  6. 6.
    Yiu, K.K., Mak, M.W., Kung, S.Y.: Environment Adaptation for Robust Speaker Verification. In: Eurospeech 2003, Geneva, pp. 2973–2976 (2003)Google Scholar
  7. 7.
    Teunen, R., Shahshahani, B., Heck, L.P.: A model based transformational approach to robust speaker recognition. In: Proc. ICSLP (2000)Google Scholar
  8. 8.
    Reynolds, D.A: Comparison of background normalization methods for text-independent speaker verification. Proceedings European Conf. on Speech Communication and Technology. Eurospeech (1997)Google Scholar
  9. 9.
    Allen, F.: Automatic Language Identification. PhD Thesis, University of New South Wales, Sydney, Australia (2005)Google Scholar
  10. 10.
    Lareau, J.: Application of Shifted Delta Cepstral Features for GMM Language Identification. MsC Thesis, Rochester Institute of Technology, USA (2006)Google Scholar
  11. 11.
    Javier, O.-G., Joaquin, G.-R., Victoria, M.-A.: AHUMADA A Large Speech Corpus in Spanish for Speaker Characterization and Identification. Speech Communication (31), 255–264 (2000)CrossRefGoogle Scholar
  12. 12.
    Bielefeld, B.: Language identification using shifted delta cepstrum. In: Proc. Fourteenth Annual Speech Research Symposium (1994)Google Scholar
  13. 13.
    Torres-Carrasquillo, P.A., Singer, E., Kohler, M.A., Greene, R.J., Reynolds, D.A., Deller Jr., J.R.: Approaches to language identification using Gaussian Mixture Models and shifted delta cepstral features. In: Proc. ICSLP, pp. 89–92 (2002)Google Scholar
  14. 14.
    Singer, E., Torres-Carrasquillo, P.A., Gleason, T.P., Campbell, W.M., Reynolds, D.A.: Acoustic, Phonetic, and Discriminative Approaches to Automatic Language Recognition. In: Proc. Eurospeech 2003, pp. 1345–1348 (2003)Google Scholar
  15. 15.
    Reynolds, D., Andrews, W., Campbell, J., Navrátil, J., Peskin, B., Adami, A., Jin, Q., Klusáček, D., Abramson, J., Mihaescu, R., Godfrey, J., Jones, D., Xiang, B.: Supersid final report: exploiting high-level information for high-performance speaker recognition. Tech. Rep. Workshop, The Centre for Language and Speech Processing (2002)Google Scholar
  16. 16.
    de Wet, F.: Additive Background Noise as a Source of non-Linear Mismatch in the Cepstral and Log-Energy Domain. Computer Speech and Language 19, 31–54 (2005)CrossRefGoogle Scholar
  17. 17.
    Martin, A., et al.: The DET curve assessment of detection task performance. Proc. of EuroSpeech 4, 1895–1898 (1997)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • José R. Calvo
    • 1
  • Rafael Fernández
    • 1
  • Gabriel Hernández
    • 1
  1. 1.Advanced Technologies Application Center, CENATAVCuba

Personalised recommendations