Principal Component Characterization of Deformation Variations Using Dynamic Imaging Atlases
Lists
Only you see this
Abstract
High-speed dynamic magnetic resonance imaging is a highly efficient tool in capturing vocal tract deformation during speech. However, automated quantification of variations in motion patterns during production of different utterances has been a challenging task due to spatial and temporal misalignments between different image datasets. We present a principal component analysis-based deformation characterization technique built on top of established dynamic speech imaging atlases. Two layers of principal components are extracted to represent common motion and utterance-specific motion, respectively. Comparison between two speech tasks with and without nasalization reveals subtle differences on velopharyngeal deformation reflected in the utterance-specific principal components.
BibTeX
@inproceedings{xing2023principal,
author = {Fangxu Xing and Riwei Jin and Imani Gilbert and Georges El Fakhri and Jamie L. Perry and Bradley P. Sutton and Jonghye Woo},
title = {{Principal Component Characterization of Deformation Variations Using Dynamic Imaging Atlases}},
booktitle = {Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition},
year = {2023},
doi = {10.58530/2022/2849},
}Loading related content...