A general data-driven procedure for creating new prosodic modules for the Italian FESTIVAL Text-To-Speech (TTS) [1] synthesizer is described. These modules are based on the "Classification and Regression Trees" (CART) theory. The prosodic factors taken into consideration are: duration, pitch and loudness. Loudness control has been implemented as an extension to the MBROLA diphone concatenative synthesizer. The prosodic models were trained using two speech corpora with different speaking style, and the effectiveness of the CART-based prosody was assessed with a set of evaluation tests.
Cite as: Tesser, F., Cosi, P., Drioli, C., Tisato, G. (2004) Prosodic data driven modelling of a narrative style in Festival TTS. Proc. 5th ISCA Workshop on Speech Synthesis (SSW 5), 185-190
@inproceedings{tesser04_ssw,
author={Fabio Tesser and Piero Cosi and Carlo Drioli and Graziano Tisato},
title={{Prosodic data driven modelling of a narrative style in Festival TTS}},
year=2004,
booktitle={Proc. 5th ISCA Workshop on Speech Synthesis (SSW 5)},
pages={185--190}
}