Sixth International Conference on Spoken Language Processing
October 16-20, 2000
A Study on the Pitch Pattern of a Singing Voice Synthesis System Based on the Cepstral Method
Tomio Takara (1), Kazuto Izumi (1), Keiichi Funaki (2)
(1) Department of Information Engineering, (2) Computing and Networking Center,
University of the Ryukyus, Nishihara, Okinawa, Japan
We synthesize singing voice by rule based on cepstral method.
Higher accuracy of analysis and synthesis is required to
synthesize singing voice, comparing to rule-based speech
synthesis. In this paper, we propose a method of analysis and
synthesis with high accuracy. Also, we express pitch patterns
minutely by curves that close to natural pitch by using this
method. We apply Fujisaki model and add vibrato to the pitch
Takara, Tomio / Izumi, Kazuto / Funaki, Keiichi (2000):
"A study on the pitch pattern of a singing voice synthesis system based on the cepstral method",
In ICSLP-2000, vol.2, 419-422.