INTERSPEECH 2007
8th Annual Conference of the International Speech Communication Association

Antwerp, Belgium
August 27-31, 2007

Inter-Language Prosodic Style Modification Experiment Using Word Impression Vector for Communicative Speech Generation

Ke Li, Yoko Greenberg, Yoshinori Sagisaka

Waseda University, Japan

To confirm the language independency of a communicative prosody generation from input word impression vector, we synthesized communicative Mandarin speech using prosodic characteristics of communicative Japanese speech. The fundamental frequency and duration characteristics of one-word "n" utterances of Japanese were copied to Mandarin through input word attributes. From the subjective impressions of an input word, a three-dimensional vector was calculated through Multi-Dimensional Scaling analysis. Three dimensions reflecting impressions of confident-doubtful, allowable-unacceptable and positive-negative correspond to systematic prosodic variations; F0 height, F0 dynamics and duration. Subjective evaluation of synthesized speech showed the possibility of communicative prosody generation from input word impression vector language independently.

Full Paper

Bibliographic reference.  Li, Ke / Greenberg, Yoko / Sagisaka, Yoshinori (2007): "Inter-language prosodic style modification experiment using word impression vector for communicative speech generation", In INTERSPEECH-2007, 1294-1297.