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

In this paper, we describe a voice transformation meth-od which changes source speaker's acoustic features to those of a target speaker. The method developed here, 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. As for nonlinear part, which represent the excitation signal, is modelled by the long-delay nonlinear predictor using a neural net. Conversion rules for excitation signal are generated by the average pitch ratio and the mapping codebook, and those for LPC cepstrum coefficients are based on the orthogonal vetctor space conversion. In addition, the spectral envelope compensation is proposed to correct spectral distortion in the transformed speech. A listening test shoots that the proposed method makes it possible to convert speaker's individuality while maintaining high quality.