Prosody Reconstruction by Rescaling Fundamental Frequency Contours in Order to Synthesize Communicative Speech

摘要

This paper presents a method of prosody reconstruction that can be used to synthesize conversational speech. In our method, we use a conventional text-to-speech engine to initially generate reading-style prosody for input text. We then use a frequency modulation technique to rescale the fundamental frequency (F{sub}0) contours to add the communicative functions of intonation to the synthesized speech. The frequency modulation technique is based on a functional F{sub}0 model, and the transformation scales are modeled by combining simple piece-wise-linear patterns according to input tags. We conducted two experiments to evaluate our method: modulating the F{sub}0 range of reading-style prosody when synthesizing Japanese speech to convey "good news" and "bad news", and making a narrow focus when synthesizing Chinese dialog to convey emphasis. The results showed that our method could use much para-linguistic information to achieve specific communicative purposes.