A deep joint sparse non-negative matrix factorization framework for identifying the common and subject-specific functional units of tongue motion during speech
Name:
Publisher version
View Source
Access full-text PDFOpen Access
View Source
Check access options
Check access options
Author
Woo, JonghyeXing, Fangxu
Prince, Jerry L
Stone, Maureen
Gomez, Arnold D
Reese, Timothy G
Wedeen, Van J
El Fakhri, Georges
Date
2021-06-12Journal
Medical Image AnalysisPublisher
Elsevier B.V.Type
Article
Metadata
Show full item recordAbstract
Intelligible speech is produced by creating varying internal local muscle groupings—i.e., functional units—that are generated in a systematic and coordinated manner. There are two major challenges in characterizing and analyzing functional units. First, due to the complex and convoluted nature of tongue structure and function, it is of great importance to develop a method that can accurately decode complex muscle coordination patterns during speech. Second, it is challenging to keep identified functional units across subjects comparable due to their substantial variability. In this work, to address these challenges, we develop a new deep learning framework to identify common and subject-specific functional units of tongue motion during speech. Our framework hinges on joint deep graph-regularized sparse non-negative matrix factorization (NMF) using motion quantities derived from displacements by tagged Magnetic Resonance Imaging. More specifically, we transform NMF with sparse and graph regularizations into modular architectures akin to deep neural networks by means of unfolding the Iterative Shrinkage-Thresholding Algorithm to learn interpretable building blocks and associated weighting map. We then apply spectral clustering to common and subject-specific weighting maps from which we jointly determine the common and subject-specific functional units. Experiments carried out with simulated datasets show that the proposed method achieved on par or better clustering performance over the comparison methods. Experiments carried out with in vivo tongue motion data show that the proposed method can determine the common and subject-specific functional units with increased interpretability and decreased size variability. © 2021Sponsors
This work is partially supported by NIH R01DC014717, R01DC018511, R01CA133015, R21DC016047, R00DC012575, P41EB022544 and NSF 1504804 PoLS .Rights/Terms
Copyright © 2021. Published by Elsevier B.V.Identifier to cite or link to this item
http://hdl.handle.net/10713/16106ae974a485f413a2113503eed53cd6c53
10.1016/j.media.2021.102131
Scopus Count
Collections
Related articles
- Identifying the Common and Subject-specific Functional Units of Speech Movements via a Joint Sparse Non-negative Matrix Factorization Framework.
- Authors: Woo J, Xing F, Prince JL, Stone M, Reese TG, Wedeen VJ, El Fakhri G
- Issue date: 2020 Feb
- A Sparse Non-Negative Matrix Factorization Framework for Identifying Functional Units of Tongue Behavior From MRI.
- Authors: Jonghye Woo, Prince JL, Stone M, Fangxu Xing, Gomez AD, Green JR, Hartnick CJ, Brady TJ, Reese TG, Wedeen VJ, El Fakhri G
- Issue date: 2019 Mar
- Determining functional units of tongue motion via graph-regularized sparse non-negative matrix factorization.
- Authors: Woo J, Xing F, Lee J, Stone M, Prince JL
- Issue date: 2014
- Differentiating post-cancer from healthy tongue muscle coordination patterns during speech using deep learning.
- Authors: Woo J, Xing F, Prince JL, Stone M, Green JR, Goldsmith T, Reese TG, Wedeen VJ, El Fakhri G
- Issue date: 2019 May
- Analysis of 3-D Tongue Motion From Tagged and Cine Magnetic Resonance Images.
- Authors: Xing F, Woo J, Lee J, Murano EZ, Stone M, Prince JL
- Issue date: 2016 Jun 1