Skip to main content

Enhancing Speaker Discrimination at the Feature Level

  • Chapter
Speaker Classification I

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 4343))

Abstract

This chapter describes a method for enhancing the differences between speaker classes at the feature level (feature enhancement) in an automatic speaker recognition system. The original Mel-frequency cepstral coefficient (MFCC) space is projected onto a new feature space by a neural network trained on a subset of speakers which is representative for the whole target population. The new feature space better discriminates between the target classes (speakers) than the original feature space. The chapter focuses on the method for selecting a representative subset of speakers, comparing several approaches to speaker selection. The effect of feature enhancement is tested both for clean and various noisy speech types to evaluate its applicability under practical conditions. It is shown that the proposed method leads to a substantial improvement in speaker recognition performance. The method can also be applied to other automatic speaker classification tasks.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Laver, J.: The Phonetic Description of Voice Quality. Cambridge University Press, Cambridge (1980)

    Google Scholar 

  2. Dellwo, V., Huckvale, M., Ashby, M.: How is individuality expressed in voice? An introduction to speech production & description for speaker classification. In: Müller, C. (ed.) Speaker Classification I. LNCS(LNAI), vol. 4343, Springer, Heidelberg (this issue, 2007)

    Google Scholar 

  3. Konig, Y., Heck, L., Weintraub, M., Sonmez, K.: Nonlinear discriminant feature extraction for robust text-independent speaker recognition. In: Proceedings of RLA2C, ESCA workshop on Speaker Recognition and its Commercial and Forensic Applications, Avignon, France, pp. 72–75 (1998)

    Google Scholar 

  4. Heck, L., Konig, Y., Kemal Sönmez, M., Weintraub, M.: Robustness to telephone handset distortion in speaker recognition by discriminative feature design. Speech Communication 31, 181–192 (2000)

    Article  Google Scholar 

  5. Garofolo, J.S., Lamel, L.F., Fisher, W.M., Fiscus, J.G., Pallett, D.S., Dahlgren, N.L., Zue, V.: TIMIT Acoustic-Phonetic Continuous Speech Corpus. Linguistic Data Consortium (1993)

    Google Scholar 

  6. Varga, A., Steeneken, H.J.M.: Assesment for automatic speech recognition: II. NOISEX-92: A database and an experiment to study the effect of additive noise on speech recognition systems. Speech Communication 12, 247–252 (1993)

    Article  Google Scholar 

  7. ITU recommendation P.56: Objective measurement of active speech level (March 1993)

    Google Scholar 

  8. Fisher, W.M., Doddington, G.R., Goudie-Mashall, K.M., Jankowski, C., Kalyanswamy, A., Basson, S., Spitz, J.: NTIMIT. Linguistic Data Consortium (1993)

    Google Scholar 

  9. Sturim, D.E., Campbell, W.M., Reynolds, D.A.: Classification methods for speaker recognition. In: Müller, C. (ed.) Speaker Classification I. LNCS(LNAI), vol. 4343, Springer, Heidelberg (this issue, 2007)

    Google Scholar 

  10. Reynolds, D.A.: Speaker identification and verification using Gaussian mixture speaker models. Speech Communication 17, 91–108 (1995)

    Article  Google Scholar 

  11. Reynolds, D.A., Zissman, M.A., Quatieri, T.F., O’Leary, G.C., Carlson, B.A.: The effect of telephone transmission degradations on speaker recognition performance. In: Proceedings ICASSP 1995, Detroit, Michigan, pp. 329–332 (1995)

    Google Scholar 

  12. Collobert, R., Bengio, S., Mariéthoz, J.: Torch: a modular machine learning software library. Technical Report IDIAP-RR 02-46 (2002)

    Google Scholar 

  13. Sharma, S., Ellis, D., Kajarekar, S., Jain, P., Hermansky, H.: Feature extraction using non-linear transformation for robust speech recognition on the Aurora database. In: Proceedings ICASSP2000, Istanbul, Turkey, pp. 1117–1120 (2000)

    Google Scholar 

  14. Wu, D., Morris, A.C., Koreman, J.: MLP internal representation as discriminative features for improved speaker recognition. In: Faundez-Zanuy, M., Janer, L., Esposito, A., Satue-Villar, A., Roure, J., Espinosa-Duro, V. (eds.) NOLISP 2005. LNCS (LNAI), vol. 3817, pp. 72–80. Springer, Heidelberg (2006)

    Chapter  Google Scholar 

  15. Morris, A.C., Wu, D., Koreman, J.: MLP trained to separate problem speakers provides improved features for speaker identification. In: ICCST 2005. Proceedings IEEE Int. Carnahan Conf. on Security Technology, Las Palmas, Spain (2005)

    Google Scholar 

  16. Wu, D.: Discriminative Preprocessing of Speech: Towards Improving Biometric Identification. Ph.D. thesis Saarland University, Saarbrücken, Germany (2007)

    Google Scholar 

  17. Theodoridis, S., Koutroumbas, K.: Pattern Recognition, 2nd edn. Elsevier Academic Press, Amsterdam (2003)

    Google Scholar 

  18. Reynolds, D.A.: Experimental evaluation of features for robust speaker identification. IEEE Transactions on Speech and Audio Processing 2, 639–643 (1994)

    Article  Google Scholar 

  19. Gillick, L., Cox, S.J.: Some statistical issues in the comparison of speech recognition algorithms. In: Proceedings ICASSP, Glasgow, pp. 532–535 (1989)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Christian Müller

Rights and permissions

Reprints and permissions

Copyright information

© 2007 Springer-Verlag Berlin Heidelberg

About this chapter

Cite this chapter

Koreman, J., Wu, D., Morris, A.C. (2007). Enhancing Speaker Discrimination at the Feature Level. In: Müller, C. (eds) Speaker Classification I. Lecture Notes in Computer Science(), vol 4343. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74200-5_15

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-74200-5_15

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-74186-2

  • Online ISBN: 978-3-540-74200-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics