Based on a set of 3D vocal tract images obtained by MRI, a 3D linear articulatory model has been built using guided Principal Component Analysis. It constitutes an extension to the lateral dimension of the mid-sagittal model previously developed from a radiofilm recorded on the same subject. The parameters of the 2D model have been found to be good predictors of the 3D shapes, for most configurations. A first evaluation of the model in terms of area functions and formants is presented.
Cite as: Badin, P., Bailly, G., Raybaudi, M., Segebarth, C. (1998) A three-dimensional linear articulatory model based on MRI data. Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998), paper 0014, doi: 10.21437/ICSLP.1998-353
@inproceedings{badin98_icslp,
author={Pierre Badin and Gérard Bailly and Monica Raybaudi and Christoph Segebarth},
title={{A three-dimensional linear articulatory model based on MRI data}},
year=1998,
booktitle={Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998)},
pages={paper 0014},
doi={10.21437/ICSLP.1998-353}
}