Artificial Intelligence Review

, Volume 27, Issue 4, pp 295–307

An evaluation of one-class classification techniques for speaker verification

  • Anthony Brew
  • Marco Grimaldi
  • Pádraig Cunningham
Article

Abstract

Speaker verification is a challenging problem in speaker recognition where the objective is to determine whether a segment of speech in fact comes from a specific individual. In supervised machine learning terms this is a challenging problem as, while examples belonging to the target class are easy to gather, the set of counter-examples is completely open. This makes it difficult to cast this as a supervised classification problem as it is difficult to construct a representative set of counter examples. So we cast this as a one-class classification problem and evaluate a variety of state-of-the-art one-class classification techniques on a benchmark speech recognition dataset. We construct this as a two-level classification process whereby, at the lower level, speech segments of 20 ms in length are classified and then a decision on an complete speech sample is made by aggregating these component classifications. We show that of the one-class classification techniques we evaluate, Gaussian Mixture Models shows the best performance on this task.

Keywords

One-class classifiers Speaker verification Gaussian mixture models 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Bimbot F, Bonastre J, Fredouille C, Gravier G, Magrin-Chagnolleau I, Meignier S, Merlin T, Ortega-Garcia J, Petrovska-Delacretaz, Reynolds D D (2004) A tutorial on text-independent speaker verification. EURASIP J Appl Signal Process 4: 430–451CrossRefGoogle Scholar
  2. Bradley AP (1997) The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recognit 30(7): 1145–1159CrossRefGoogle Scholar
  3. Cummins F, Grimaldi M, Leonard T, Simko J (2006) The CHAINS corpus: CHAracterizing INdividual Speakers. In: Proceedings of SPECOM’06, pp 431–435Google Scholar
  4. Kittler J, Hatef M, Duin RPW, Matas J (1998) On combining classifiers. Pattern Anal Mach Intell IEEE Trans 20(3): 226–239CrossRefGoogle Scholar
  5. Reynolds D (1995) Speaker identification and verification using Gaussian mixture speaker models. Speech Commun 17(1): 91–108CrossRefGoogle Scholar
  6. Reynolds D (2002) An overview of automatic speaker recognition technology. In: Proceedings of the International Conference on Acoustics, Speech, and Signal ProcessingGoogle Scholar
  7. Reynolds DA (2003) Channel robust speaker verification via feature mapping. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP ’03), vol 2, pp II–53–6Google Scholar
  8. Reynolds DA, Rose RC (1995) Robust text-independent speaker identification using gaussian mixture speaker models. Speech Audio Process IEEE Trans 3(1): 72–83CrossRefGoogle Scholar
  9. Reynolds DA, Quatieri TF, Dunn RB (2000) Speaker verification using adapted gaussian mixture models. Digital Signal Processing, pp 19–41Google Scholar
  10. Taniguchi M, Tresp V (1997) Averaging regularized estimators. Neural Comput 9(5): 1163–1178CrossRefGoogle Scholar
  11. Tax DMJ (2001) One-class classification. Ph.D. thesis, Delft University of TechnologyGoogle Scholar
  12. Tax DMJ, Duin RPW (1999) Support vector domain description. Pattern Recogn Lett 20(11–13): 1191–1199CrossRefGoogle Scholar
  13. Tax DMJ, Muller KR (2004) A consistency-based model selection for one-class classification. In: Proceedings of the 17th International Conference on Pattern Recognition (ICPR 2004), vol 3, pp 363–366Google Scholar
  14. Wan V, Renals S (2005) Speaker verification using sequence discriminant support vector machines. Speech Audio Process IEEE Trans 13(2): 203–210CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media B.V. 2008

Authors and Affiliations

  • Anthony Brew
    • 1
  • Marco Grimaldi
    • 1
  • Pádraig Cunningham
    • 1
  1. 1.Department of Computer Science and InformaticsUniversity College DublinDublinIreland

Personalised recommendations