Voice conversion by codebook mapping of line spectral frequencies and excitation spectrum

This paper presents a new scheme for developing a voice conversion system that modiies the utterance of a source speaker to sound like speech from a target speaker. We refer to the method as Speaker Transformation Algorithm using Segmen-tal Codebooks (STASC). Two new methods are described to perform the transformation of vocal tract and glottal excita-tion characteristics across speakers. In addition, the source speaker's general prosodic characteristics are modiied using timescale and pitch-scale modiication algorithms. Informal listening tests suggest that convincing voice conversion is achieved while maintaining high speech quality. The performance of the proposed system is also evaluated on a standard Gaussian mixture model based speaker identiication system, and the results show that the transformed speech is assigned higher likelihood by the target speaker model when compared to the source model.