ISCA Archive ICSLP 2000
ISCA Archive ICSLP 2000

A study on the pitch pattern of a singing voice synthesis system based on the cepstral method

Tomio Takara, Kazuto Izumi, Keiichi Funaki

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 pattern.


Cite as: Takara, T., Izumi, K., Funaki, K. (2000) A study on the pitch pattern of a singing voice synthesis system based on the cepstral method. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 2, 419-422

@inproceedings{takara00b_icslp,
  author={Tomio Takara and Kazuto Izumi and Keiichi Funaki},
  title={{A study on the pitch pattern of a singing voice synthesis system based on the cepstral method}},
  year=2000,
  booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
  pages={vol. 2, 419-422}
}