ISCA Archive ICSLP 2000
ISCA Archive ICSLP 2000

Natural F0 contours with a new neural-network-hybrid approach

Caglayan Erdem, Martin Holzapfel, RĂ¼diger Hoffmann

Text-to-Speech (TTS) systems still suffer from unnatural prosody generation. To increase customers acceptance a more sophisticated prosody modelling is required. In this paper a new hybrid approach combining the advantages of two existing state-of-the-art modelling strategies is presented.

After presenting two state-of-the-art approaches with their advantages and shortcomings in section 1 we will discuss the new architecture of the hybrid approach in section 2 outlining the data driven interconnection of the two base approaches. Finally a search performed on the database will be presented using a fuzzy motivated nonlinear parametric cost and suitability function for obtaining desired fo-control parameters. The hybrid approach improved our fo-generation Module within our TTS system PAPAGENO.


Cite as: Erdem, C., Holzapfel, M., Hoffmann, R. (2000) Natural F0 contours with a new neural-network-hybrid approach. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 3, 227-230

@inproceedings{erdem00_icslp,
  author={Caglayan Erdem and Martin Holzapfel and RĂ¼diger Hoffmann},
  title={{Natural F0 contours with a new neural-network-hybrid approach}},
  year=2000,
  booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
  pages={vol. 3, 227-230}
}