Probabilistic speech F₀ contour model incorporating statistical vocabulary model of phrase-accent command sequence

Tatsuma Ishihara, Hirokazu Kameoka, Kota Yoshizato, Daisuke Saito, Shigeki Sagayama

We have previously proposed a generative model of speech F0 contours, based on the discrete-time version of the Fujisaki model (a model of the mechanism for controlling F0s through laryngeal muscles). One advantage of this model is that it allows us to apply statistical methods to estimate the Fujisaki-model parameters from speech F0 contours. This paper proposes a new generative model of speech F0 contours incorporating a vocabulary model of intonation patterns. A parameter inference algorithm for the present model is derived. We quantitatively evaluated the performance of our parameter inference algorithm.

doi: 10.21437/Interspeech.2013-110

Cite as: Ishihara, T., Kameoka, H., Yoshizato, K., Saito, D., Sagayama, S. (2013) Probabilistic speech F₀ contour model incorporating statistical vocabulary model of phrase-accent command sequence. Proc. Interspeech 2013, 1017-1021, doi: 10.21437/Interspeech.2013-110

@inproceedings{ishihara13_interspeech,
  author={Tatsuma Ishihara and Hirokazu Kameoka and Kota Yoshizato and Daisuke Saito and Shigeki Sagayama},
  title={{Probabilistic speech F0 contour model incorporating statistical vocabulary model of phrase-accent command sequence}},
  year=2013,
  booktitle={Proc. Interspeech 2013},
  pages={1017--1021},
  doi={10.21437/Interspeech.2013-110}
}