Sixth International Conference on Spoken Language Processing
October 16-20, 2000
Learning the Parameters of Quantitative Prosody Models
Oliver Jokisch, Hansjörg Mixdorff, Hans Kruschke, Ulrich Kordon
Laboratory of Acoustics and Speech Communication, Dresden University of Technology, Germany
The article introduces a novel hybrid data driven and rule
based approach for the prosody control in a TTS system,
which combines the advantages of well-balanced, quantitative
models with the flexible training of derived model parameters.
Instancing the training of Fujisaki intonation parameters for
German (MFGI) the article describes the hybrid data driven
and rule based architecture HYDRA, the speech database, the
extraction of the model parameters and the neural network
(NN) training of these parameters. Preliminary results using
the hybrid intonation model are presented. A hybrid neural
network and rule based, quantitative model can be easily
parameterized and adapted e.g. for multilingual applications,
but has a higher complexity and requires the automatic
extraction of the model parameters from a speech database.
Jokisch, Oliver / Mixdorff, Hansjörg / Kruschke, Hans / Kordon, Ulrich (2000):
"Learning the parameters of quantitative prosody models",
In ICSLP-2000, vol.1, 645-648.