Clustering Target Speaker on a Set of Telephone Dialogs

  • Andrey Shulipa
  • Aleksey Sholohov
  • Yuri Matveev
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10458)


The ability of the speaker’s voice model to reproduce detailed parameterization of individual speech features is an important property for its use in solving different biometric problems. In general case one of the main reasons of performance degradation in voice biometric systems is the voice variability that occurs when speaker’s state (emotional, physiological, etc.) or channel conditions are changing. Therefore, accurate modeling of the intra-speaker voice variability leads to a more accurate voice model. This can be achieved by collecting multiple speech samples of the same speaker recorded in diverse conditions to create so-called multi-session model. We consider the case when speech data is represented by dialogues recorded in a single channel. This setup raises the problem of grouping the segments of a target speaker from the set of dialogues. We propose a clustering algorithm to solve this problem, which is based on the probabilistic linear discriminant analysis (PLDA). Our experiments demonstrate effectiveness of the proposed approach compared to solutions based on exhaustive search.


Speaker recognition Voice model Clusterization 



This work was financially supported by the Ministry of Education and Science of the Russian Federation, Contract 14.578.21.0126 (ID RFMEFI57815X0126).


  1. 1.
    Jain, A.K., Ross, A., Prabhakar, S.: An Introduction to biometric recognition. IEEE Trans. Circuits Syst. Video Technol. 14(1), 4–20 (2004)CrossRefGoogle Scholar
  2. 2.
    Batchelor, J., Lee, D., Banks, D., Crosby, D., Moore, K., Kuhn, S., Rodriguez, T., Stephens, A.: Investigative Report. Florida Department of Law Enforcement (2012)Google Scholar
  3. 3.
    Averbouch, D., Kahn, J.: Fraud targets the contact center: What now? Speech Technology Magazine, November 2013Google Scholar
  4. 4.
    SESTEK, the rise of voice biometrics as a key security solution. Speech Technology Magazine (2013)Google Scholar
  5. 5.
    Kenny, P., Reynolds, D., Castaldo, F.: Diarization of telephone conversations using factor analysis. Sel. Top. Sign. Process. 4(6), 1059–1070 (2010)CrossRefGoogle Scholar
  6. 6.
    Kenny, P.: Bayesian analysis of speaker diarization with eigenvoice priors. CRIM, Montreal, Technical report (2008)Google Scholar
  7. 7.
    Zheng, R., Zhang, C., Zhang, S., Xu, B.: Variational bayes based i-vector for speaker diarization of telephone conversations. In: IEEE International Conference Acoustics, Speech and Signal Processing (2014)Google Scholar
  8. 8.
    Kenny, P.: Joint factor analysis of speaker and session variability: Theory and algorithms. Technical report CRIM-06/08-13 (2005).
  9. 9.
    Dehak, N., Kenny, P., Dehak, R., Dumouchel, P., Ouellet, P.: Front-end factor analysis for speaker verification. IEEE Trans. Audio Speech Lang. Process. 19(4), 788–798 (2011)CrossRefGoogle Scholar
  10. 10.
    Kenny, P.: Bayesian speaker verification with heavy tailed priors. In: Speaker and Language Recognition Workshop. IEEE, Odyssey (2010)Google Scholar
  11. 11.
    Prince, S.J., Elder, J.H.: Probabilistic linear discriminant analysis for inferences about identity. In: Proceeding of ICCV, pp. 1–8. IEEE (2007)Google Scholar
  12. 12.
    Zhang, S., Zhang, C., Zheng, R., Xu, B.: An investigation of summed-channel speaker recognition with multi-session enrollment. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1640–1644 (2014)Google Scholar
  13. 13.
    Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, New York (2006)zbMATHGoogle Scholar
  14. 14.
    Kozlov, A., et al.: SVID speaker recognition system for NIST SRE 2012. In: Speech and Computer: 15th International Conference (SPECOM), pp. 278–285 (2013)Google Scholar
  15. 15.
  16. 16.
    Sholokhov, A., Pekhovsky, T., Kudashev, O., Shulipa, A., Kinnunen, T.: Bayesian analysis of similarity matrices for speaker diarization. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 106–110 (2014)Google Scholar
  17. 17.
    Novoselov, S., Pekhovsky, T., Simonchik, K., Shulipa, A.: RBM-PLDA subsystem for the NIST i-vector challenge. In: Annual Conference of the International Speech Communication Association, pp. 378–382 (2014)Google Scholar
  18. 18.
    Novoselov, S., Pekhovsky, T., Shulipa, A., Kudashev, O.: Plda-based system for text-prompted password speaker verification. In: International Conference on Advance Video- and Signal-based Surveillance (AVSS), pp. 1–5 (2015)Google Scholar
  19. 19.
    Pekhovsky, T., Sizov, A.: Comparison of various mixtures of Gaussian PLDA-models in the problem of text-independent speaker verification. J. Instrum. Eng. 56(2), 51–61 (2013)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Andrey Shulipa
    • 1
  • Aleksey Sholohov
    • 1
  • Yuri Matveev
    • 1
    • 2
  1. 1.ITMO UniversitySaint PetersburgRussia
  2. 2.STC-innovations Ltd.Saint PetersburgRussia

Personalised recommendations