Pseudo Multi Parallel Branch HMM for Speaker Verification

  • Donato Impedovo
  • Mario Refice
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 57)


This paper describes an approach, called Pseudo Multi Parallel Branch (P-MPB) Model, for coping with performance degradation typically observed over (short and medium) time and trials in Text Dependent Speaker Verification’s task. It is based on the use of a fused HMM model having a multi parallel branch topology where each branch consists of an HMM referring to a specific frame’s length representation of the speaker. The approach shows reasonable ER’s reduction from the baseline system.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Boyer, K.W., Govindaraju, V., Ratha, N.K.: Special Issue on Recent Advances in Biometric Systems. IEEE Trans. on System, Man and Cybernetics - Part B 37(5) (2007)Google Scholar
  2. 2.
    Prabhakar, S., Kittler, J., Maltoni, D., O’Gorman, L., Tan, T. (eds.): Special Issue on Biometrics: Progress and Directions. IEEE Trans. on PAMI 29(4) (2007)Google Scholar
  3. 3.
    Jain, A.K., Flynn, P., Ross, A.: Handbook of Biometrics. Springer, Heidelberg (2007)Google Scholar
  4. 4.
    Bigeco, M., Grosso, E., Tistarelli, M.: Person authentication from video of faces: a behavioural and physiological approach using Pseudo Hierarchical Hidden Markov Models. In: Zhang, D., Jain, A.K. (eds.) ICB 2005. LNCS, vol. 3832, pp. 113–120. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  5. 5.
    Impedovo, D., Pirlo, G., Refice, M.: Handwritten Signature and Speech: Preliminary Experiments on Multiple Source and Classifiers for Personal Identity Verification. In: Srihari, S.N., Franke, K. (eds.) IWCF 2008. LNCS, vol. 5158, pp. 181–191. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  6. 6.
    Campbell, J.P.: Speaker Recognition: A tutorial. Proceedings of IEEE, 1437–1462 (1997)Google Scholar
  7. 7.
    Reynolds, D.A.: Speaker Identification and Verification using Gaussian Mixture Speaker Models. Speech Communication, 91–108 (1995)Google Scholar
  8. 8.
    Rabiner, L.R.: A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE 77(2), 257–286 (1989)CrossRefGoogle Scholar
  9. 9.
    Reynolds, D.A.: An overview of Automatic Speaker Recognition Technology. In: IEEE Proc. of International Conference of Speech, Acoustic and Signal Processing, vol. 4, pp. 4072–4075 (2002)Google Scholar
  10. 10.
    Chen, K.: On the Use of Different Speech Representations for Speaker Modeling. IEEE Trans. on System, Man and Cybernetics, Part C: Applications and Reviews 35(3), 301–314 (2005)CrossRefGoogle Scholar
  11. 11.
    Impedovo, D., Refice, M.: Speaker Identification by Multi-Frame Generative Models. In: IEEE Proc. of the 4th International Conference on Information Assurance and Security (IAS 2008), September 8-10, pp. 27–32 (2008)Google Scholar
  12. 12.
    Impedovo, D., Refice, M.: Frame Length Selection in Speaker Verification Task. Transaction on Systems 7(10), 1028–1037 (2008)Google Scholar
  13. 13.
    Impedovo, D., Refice, M.: The Influence of Frame Length on Speaker Identification Performance. In: IEEE Proc. of the Fourth International Symposium on Information Assurance and Security, pp. 435–438 (2007)Google Scholar
  14. 14.
    Pelecanos, J., Slomka, S., Sridharan, S.: Enhancing Automatic Speaker Identification using Phoneme Clustering and Frame Based Parameter and Frame Size Selection. In: IEEE Proc. of the Fifth International Symposium on Signal Processing and its Applications, pp. 633–636 (1999)Google Scholar
  15. 15.
    Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society, Series B 39(1), 1–38 (1977)zbMATHMathSciNetGoogle Scholar
  16. 16.
    Fine, S., Singer, Y., Tishby, N.: The Hierarchical Hidden Markov Model: Analysis and Applications. Machine Learning 32, 41–62 (1998)CrossRefzbMATHGoogle Scholar
  17. 17.
    Wang, W., Brakensiek, A., Kosmala, A., Rigoll, G.: Multi-Branch and Two-Pass HMM Modeling Approaches for Off-Line Cursive Handwriting Recognition. In: IEEE Proc. of the 6th International Conference on Document Analysis and Recognition (ICDAR), pp. 231–235 (2001)Google Scholar
  18. 18.
    Kinnunen, T., Karpov, E., Franti, P.: Real-Time Speaker Identification and Verification. IEEE Trans. on Audio, Speech and Language Processing 14(1), 277–288 (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Donato Impedovo
    • 1
  • Mario Refice
    • 1
  1. 1.DEE Dipartimento di Elettrotecnica ed ElettronicaPolitecnico di BariBariItaly

Personalised recommendations