“Interactive speech conversion system cloning speaker intonation automatically” by Adachi and Morishima
Conference:
Type(s):
Title:
- Interactive speech conversion system cloning speaker intonation automatically
Presenter(s)/Author(s):
Abstract:
In this paper, we present an interactive speech conversion system that can modify emotinal factors, emphasize utterances, and append a dialect. This system converts the prosody of stored sample voice into a new prosody given by realtime analysis of microphone captured reference voice. Only intonations are controlled by converting utterance speed, pitch, and power of speech with keeping a characteristic of the speaker’s and linguistic information as an original. Especially, an interpolation method of utterance speed is originally proposed and a quality of synthesized speech is as good as original after subjective evaluation.
