Voice Conversion Based on Hybrid SVR and GMM

Downloads

Authors

  • Peng SONG Key Laboratory of Underwater Acoustic Signal Processing of Ministry of Education Southeast University
  • Yun JIN School of Physics and Electronic Engineering, Xuzhou Normal University; Key Laboratory of Child Development and Learning Science of Ministry of Education Southeast University
  • Li ZHAO Key Laboratory of Underwater Acoustic Signal Processing of Ministry of Education Southeast University
  • Cairong ZOU Key Laboratory of Underwater Acoustic Signal Processing of Ministry of Education Southeast University

Abstract

A novel VC (voice conversion) method based on hybrid SVR (support vector regression) and GMM (Gaussian mixture model) is presented in the paper, the mapping abilities of SVR and GMM are exploited to map the spectral features of the source speaker to those of target ones. A new strategy of F0 transfor- mation is also presented, the F0s are modeled with spectral features in a joint GMM and predicted from the converted spectral features using the SVR method. Subjective and objective tests are carried out to evaluate the VC performance; experimental results show that the converted speech using the proposed method can obtain a better quality than that using the state-of-the-art GMM method. Meanwhile, a VC method based on non-parallel data is also proposed, the speaker-specific information is investigated us- ing the SVR method and preliminary subjective experiments demonstrate that the proposed method is feasible when a parallel corpus is not available.

Keywords:

voice conversion, support vector regression, Gaussian mixture model, F0 prediction, speaker- specific information