Development of Continuous Voice Morphing Using Separated Vocal TractArea Functions, Glottal Source Waves, and Prosodic Features

点击翻译按钮获取中文摘要

In this project, we have developed a flexible voice morphing method, which is based on a conversion using a linear combination of the vocal tract area functions estimated from speech signals and targeted on realization of the continuity of the phonological identity of the overall interpolated area. The main features of the method are,1) to separate characteristics of the vocal tract resonances from those of glottal source waves,2) independent morphing of the vocal tract resonances and glottal source wave characteristics, and 3) conversion method of prosodic features based on DCT(digital cosinetransform) domain. We have established that a morphing system constructed from the proposed method improves the continuity of the phonological identity and the speech quality in the intermediate morphing rate.