The Superposition of Functional Contours (SFC) prosody model decomposes the intonation and duration contours into elementary contours that encode specific linguistic functions. It is based on training a set of contour generators trained in an analysis-by-synthesis loop. The model has been proven to be able to extract these functional contours for multiple linguistic tasks and for multiple languages. It has also been successfully used to decompose and then synthesise visual prosody in terms of facial expression. PySFC is a fully functional prosody analysis system built around the SFC that is completely free software. It is created to ease access to the SFC model for the speech research community, and to facilitate further development of decompositional prosody models.
Cite as: Gerazov, B., Bailly, G. (2018) PySFC - A System for Prosody Analysis based on the Superposition of Functional Contours Prosody Model. Proc. Speech Prosody 2018, 774-778, doi: 10.21437/SpeechProsody.2018-157
@inproceedings{gerazov18_speechprosody,
author={Branislav Gerazov and Gérard Bailly},
title={{PySFC - A System for Prosody Analysis based on the Superposition of Functional Contours Prosody Model}},
year=2018,
booktitle={Proc. Speech Prosody 2018},
pages={774--778},
doi={10.21437/SpeechProsody.2018-157}
}