Data-driven generation of F0 contours using a superpositional model

  title={Data-driven generation of F0 contours using a superpositional model},
  author={Atsuhiro Sakurai and Keikichi Hirose and Nobuaki Minematsu},
  journal={Speech Communication},
This paper introduces a novel model-constrained, data-driven method to generate fundamental frequency contours for Japanese text-to-speech synthesis. In the training phase, the relationship between linguistic features and the parameters of a command–response F0 contour generation model is learned by a prediction module, which is represented by either a neural network or a set of binary regression trees. Input features consist of linguistic information related to accentual phrases that can be… CONTINUE READING
Highly Cited
This paper has 36 citations. REVIEW CITATIONS
19 Extracted Citations
23 Extracted References
Similar Papers

Citing Papers

Publications influenced by this paper.
Showing 1-10 of 19 extracted citations

Referenced Papers

Publications referenced by this paper.
Showing 1-10 of 23 references

J-ToBI: An intonation labelling system for Japanese

  • N. Campbell, J. Venditti
  • Fall Mtg. Acoust. Soc. Jpn,
  • 1995
Highly Influential
9 Excerpts

A system for the synthesis of high-quality speech from texts on general weather conditions

  • K. Hirose, H. Fujisaki
  • IEICE Trans. Fundam. E-76-A,
  • 1993
Highly Influential
4 Excerpts

The fundamental frequency contour of speech––its modeling, underlying mechanisms, and application to multilingual speech synthesis

  • H. Fujisaki
  • Proc. Int. Conf. Speech Process., Seoul
  • 1999
2 Excerpts

Similar Papers

Loading similar papers…