Hideyuki Mizuno;Masanobu Abe
-;-
A comparison of spectral smoothing methods for segment concatenation based speech synthesis
Speech Communication
Non-linear frequency scale mapping for voice conversion in text-to-speech system with cepstral description
A HMM-WDLT framework for HNM-based voice conversion with parametric adjustment in formant bandwidth, duration and excitation
International Journal of Speech Technology