Voice Conversion Using K-Histograms and Residual Averaging

Abstract

The main goal of a voice conversion system is to modify the voice of a source speaker, in order to be perceived as if it had been uttered by another specific speaker. Many approaches found in the literature convert only the features related to the vocal tract of the speaker. Our proposal is to convert those characteristics of the vocal tract, and also to process the signal passing through the vocal chords. Thus, the goal of this work is to obtain better scores in the voice conversion results.