Continuous Voice Morphing Using Separated Vocal Tract Area Functions and Glottal Source Waves
Kazuyo Tanaka, Yoshiki Nambu · 2013
This paper presents 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. The method focuses on 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 using AR-HMM analysis of speech, 2) independent morphing of the vocal tract resonances and glottal source wave characteristics, and 3) a non-linear interpolation in a log vocal tract area function domain. The method employs a statistical mapping on the log vocal tract area function domain and the cepstrum domain for the glottal source wave. We establish that a morphing system constructed from the proposed method improves the continuity of formants and the speech quality in the intermediate morphing rate.