A new voice transformation method based on both linear and nonlinear prediction analysis

We describe a voice transformation method which changes the source speaker´s acoustic features to those of a target speaker. In the method acoustic features are divided into two parts, linear and nonlinear parts. Linear parts are characterized by LPC cepstrum coefficients which are obtained from LP analysis. The nonlinear part, which represents the excitation signal, is modelled by the long-delay nonlinear predictor using a neural net. Conversion rules for the excitation signal are generated by the average pitch ratio and the mapping codebook, and those for LPC cepstrum coefficients are based on the orthogonal vector space conversion. In addition, the spectral envelope compensation is proposed to correct spectral distortion. In the transformed speech a listening test shows that the proposed method makes it possible to convert speaker´s individuality while maintaining high quality