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.
Publication type:
Contributo in volume
Publisher:
IEEE, New York, USA
Source:
Proceedings of 2002 IEEE Workshop on Speech Syntesis, pp. 131–134. New York: IEEE, 2002
Date:
2002
Resource Identifier:
http://www.cnr.it/prodotto/i/93614
http://www2.pd.istc.cnr.it/Papers/PieroCosi/cp-IEEE-SPSS2002.pdf
urn:isbn:0-7803-7395-2
Language:
Eng
ISTC Author:
Real name:
Real name: