This study compares four automatic methods for estimating Fujisaki-model parameters. Since interpolation and smoothing are necessary prerequisites for all approaches their fitting accuracies are also compared with that of a novel stylisation method. A hand-corrected set of results from one of the methods which was created on linguistic grounds served as a second benchmark. Although the four methods yield comparable results with respect to their total errors, they show different error distributions. The manually corrected version provided a poorer approximation of the F0 contours than the automatic one.
Cite as: Pfitzinger, H.R., Mixdorff, H., Schwarz, J. (2009) Comparison of Fujisaki-model extractors and F0 stylizers. Proc. Interspeech 2009, 2455-2458, doi: 10.21437/Interspeech.2009-313
@inproceedings{pfitzinger09_interspeech,
author={Hartmut R. Pfitzinger and Hansjörg Mixdorff and Jan Schwarz},
title={{Comparison of Fujisaki-model extractors and F0 stylizers}},
year=2009,
booktitle={Proc. Interspeech 2009},
pages={2455--2458},
doi={10.21437/Interspeech.2009-313}
}