First Steps Towards New Czech Voice Conversion System

  • Zdeněk Hanzlíček
  • Jindřich Matoušek
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4188)


In this paper we deal with initial experiments on creating a new Czech voice conversion system. Voice conversion (VC) is a process which modifies the speech signal produced by one (source) speaker so that it sounds like another (target) speaker. Using VC technique a new voice for speech synthesizer can be prepared with no need to record a huge amount of new speech data. The transformation is determined using equal sentences from both speakers; these sentences are time-aligned using modified dynamic time warping algorithm. The conversion is divided into two stages corresponding to the source-filter model of speech production. Within this work we employ conversion function based on Gaussian mixture model for transforming the spectral envelope described by line spectral frequencies. Residua are converted using so called residual prediction techniques. Unlike in other similar research works, we predict residua not from the transformed spectral envelope, but directly from the source speech. Four versions of residual prediction are described and compared in this study. Objective evaluation of converted speech using performance metrics shows that our system is comparable with similar existing VC systems.


Gaussian Mixture Model Dynamic Time Warping Residual Signal Speech Data Source Speech 
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.
    Stylianou, Y., Cappé, O., Moulines, E.: Continuous Probabilistic Transform for Voice Conversion. IEEE Transactions on Speech and Audio Processing 6(2), 131–142 (1998)CrossRefGoogle Scholar
  2. 2.
    Kain, A., Macon, M.W.: Spectral Voice Conversion for Text-to-Speech Synthesis. In: Proceedings of ICASSP 1998, pp. 285–288 (1998)Google Scholar
  3. 3.
    Kain, A., Macon, M.W.: Design and Evaluation of Voice Conversion Algorithm Based on Spectral Envelope Mapping and Residual Prediction. In: Proceedings of ICASSP 2001 (2001)Google Scholar
  4. 4.
    Kain, A.: High Resolution Voice Transformation. Ph.D. thesis, Oregon Health & Science University, Portland, USA (2001)Google Scholar
  5. 5.
    Gillett, B., King, S.: Transforming Voice Quality. In: Proceedings of Eurospeech 2003, pp. 1713–1716 (2003)Google Scholar
  6. 6.
    Sündermann, D., Bonafonte, A., Ney, H., Höge, H.: A Study on Residual Prediction Techniques for Voice Conversion. In: Proceedings of ICASSP 2005, pp. 13–16 (2005)Google Scholar
  7. 7.
    Sündermann, D., Höge, H., Bonafonte, A., Duxans, H.: Residual Prediction. In: Proceedings of ISSPIT 2005 (2005)Google Scholar
  8. 8.
    Ney, H., Sündermann, D., Bonafonte, A., Höge, H.: A First Step towards Text-Independent Voice Conversion. In: Proceedings of Interspeech 2004, pp. 1173–1176 (2004)Google Scholar
  9. 9.
    Vích, R., Vondra, M.: Voice Conversion Based on Nonlinear Spectrum Transformation. In: Proceedings of 14th Czech-German Workshop, pp. 53–60 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Zdeněk Hanzlíček
    • 1
  • Jindřich Matoušek
    • 1
  1. 1.Department of CyberneticsUniversity of West BohemiaPlzeňCzech Republic

Personalised recommendations