Corpus-Based Synthesis of Fundame Japanese Using Automatically-Gene Generation Proce

We have been developing corpus-based synthesis of fundamental frequency (F0) contours for Japanese. Since, in our method, the synthesis is done under the constraint of F0 contour generation process model, a rather good quality is still kept even if the prediction process is done poorly. Although it was already shown that the synthesized F0 contours sounded as highly natural as those using heuristic rules carefully arranged by experts, the F0 model parameters for the training corpus were extracted with some manual processes. In the current paper, the automatically extracted parameters are used, and a good result is obtained. Also several features are added as the inputs to the statistical method to obtain better results. Some results on the accent phrase boundary prediction in the similar corpus-based framework are also shown. 1