Fast Speaker Adaptation Using Multi-stream Based Eigenvoice in Noisy Environments

  • Hwa Jeon Song
  • Hyung Soon Kim
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4188)


In this paper, the multi-stream based eigenvoice method is proposed in order to overcome the weak points of conventional eigenvoice and dimensional eigenvoice methods in fast speaker adaptation. In the proposed method, multi-streams are automatically constructed by a method of the statistical clustering analysis that uses the information acquired by correlation between dimensions. To obtain the reliable distance matrix from the covariance matrix in order to divide full dimensions into the optimal number of streams, MAP adaptation technique is employed on the covariance matrix of training data and the sample covariance of adaptation data. According to vocabulary-independent word recognition experiment with several car noise levels and supervised adaptation mode, we obtained 29% and 31% relative improvements with 5 and 50 adaptation words at 20dB SNR in comparison with conventional eigenvoice, respectively. We also obtained 26% and 53% relative improvements with 5 and 50 adaptation words at 10dB SNR, respectively.


Noisy Environment Adaptation Data Full Dimension Linkage Algorithm Adaptation Word 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Lee, C.H., Lin, C.H., Juang, B.H.: A study on speaker adaptation of the parameters of continuous density hidden Markov models. IEEE Trans. Signal Processing 39(4), 806–814 (1991)CrossRefGoogle Scholar
  2. 2.
    Leggetter, C.J., Woodland, P.C.: Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models. Computer Speech and Language 9(1), 171–185 (1995)CrossRefGoogle Scholar
  3. 3.
    Kuhn, R., Jungua, J.C., Nguyen, P., Niedzielski, N.: Rapid speaker adaptation in eigenvoice space. IEEE Trans. Speech and Audio Processing 8(6), 695–707 (2000)CrossRefGoogle Scholar
  4. 4.
    Park, J.S., Song, H.J., Kim, H.S.: Performance improvement of rapid speaker adaptation based on eigenvoice and bias compensation. In: Proc. EuroSpeech, pp. 1481–1484 (2003)Google Scholar
  5. 5.
    Song, H.J., Kim, H.S.: Simultaneous Estimation of Weights of Eigenvoices and Bias Compensation Vector for Rapid Speaker Adaptation. In: Proc. ICSLP (2004)Google Scholar
  6. 6.
    Johnson, R.A., Wichern, D.W.: Applied Multivariate Statistical Analysis, 4th edn. Prentice-Hall, Englewood Cliffs (1998)Google Scholar
  7. 7.
    Lim, Y., Lee, Y.: Implementation of the POW (Phonetically Optimized Words) algorithm for speech database. In: Proc. ICASSP, vol. 1, pp. 89–91 (1995)Google Scholar
  8. 8.
    ITU recommendation P.56: Objective measurement of active speech level (1993)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Hwa Jeon Song
    • 1
  • Hyung Soon Kim
    • 2
  1. 1.Research Institute of Computer Information and CommunicationsPusan National UniversityBusanKorea
  2. 2.Department Electronics EngineeringPusan National UniversityBusanKorea

Personalised recommendations