Abstract
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.
Support for this work was provided by the Academy of Sciences of the Czech Republic, project No. 1ET101470416.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Stylianou, Y., Cappé, O., Moulines, E.: Continuous Probabilistic Transform for Voice Conversion. IEEE Transactions on Speech and Audio Processing 6(2), 131–142 (1998)
Kain, A., Macon, M.W.: Spectral Voice Conversion for Text-to-Speech Synthesis. In: Proceedings of ICASSP 1998, pp. 285–288 (1998)
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)
Kain, A.: High Resolution Voice Transformation. Ph.D. thesis, Oregon Health & Science University, Portland, USA (2001)
Gillett, B., King, S.: Transforming Voice Quality. In: Proceedings of Eurospeech 2003, pp. 1713–1716 (2003)
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)
Sündermann, D., Höge, H., Bonafonte, A., Duxans, H.: Residual Prediction. In: Proceedings of ISSPIT 2005 (2005)
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)
Vích, R., Vondra, M.: Voice Conversion Based on Nonlinear Spectrum Transformation. In: Proceedings of 14th Czech-German Workshop, pp. 53–60 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hanzlíček, Z., Matoušek, J. (2006). First Steps Towards New Czech Voice Conversion System. In: Sojka, P., Kopeček, I., Pala, K. (eds) Text, Speech and Dialogue. TSD 2006. Lecture Notes in Computer Science(), vol 4188. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11846406_48
Download citation
DOI: https://doi.org/10.1007/11846406_48
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-39090-9
Online ISBN: 978-3-540-39091-6
eBook Packages: Computer ScienceComputer Science (R0)