A MODIFIED "PaIntE" MODEL FOR ITALIAN TTS

Piero Cosi, Cinzia Avesani, Fabio Tesser, Roberto Gretter, Fabio Pianesi


IEEE 2002 WORKSHOP ON SPEECH SYNTHESIS

Santa Monica, California, September 11-13, 2002


Abstract

In this work, a slightly modified version of the original PaIntE model, based on an F0 parametrization with an especially designed approximation function, is considered. The model's parameters have been automatically optimized using a small set of Italian ToBI labeled sentences. This method, will drive our ongoing data-based approach to intonation modeling for Italian TTS. The quality of the model has been assessed by numerical measures and preliminary tests show quite promising results.

IRST Tech. Rep. No. 0208-25


paper (file .doc, 163 kByte)