A trainable prosodic model called SFC (Superposition of Functional Contours), proposed by Holm and Bailly, is here confronted to German intonation. Training material is the publicly available Siemens Synthesis Corpus that provides spoken utterances for high-quality speech synthesis. We describe the labeling framework and first evaluation results that compares the original prosody of test sentences of this corpus with their prosodic rendering by the proposed model and state-of-the-art systems available on-line on the web.
Cite as: Bailly, G., Gorisch, J. (2006) Generating German intonation with a trainable prosodic model. Proc. Interspeech 2006, paper 2017-Thu1FoP.3, doi: 10.21437/Interspeech.2006-593
@inproceedings{bailly06_interspeech,
author={Gérard Bailly and Jan Gorisch},
title={{Generating German intonation with a trainable prosodic model}},
year=2006,
booktitle={Proc. Interspeech 2006},
pages={paper 2017-Thu1FoP.3},
doi={10.21437/Interspeech.2006-593}
}