Wavelet-based Robust Voice conversion systems

Voice conversion is a method used to transform one speaker''s voice into another speaker''s voice. New modification approach for voice conversion is proposed in this paper. We take Mel-frequency Discrete Wavelet coefficients (MFDWC) as the basic feature. This feature copes well with small training sets of high dimension, which is a problem often encountered in voice conversion. The proposed voice conversion system consists of both off-line (training) and on-line (transformation-synthesis) procedures and assumes parallel training data from source and target speakers and uses the theory of wavelets in order to extract speaker feature information. The satisfactory performance of the voice conversion system can be confirmed through ABX listening test and MOS grade.