Predicting Tongue Motion in Unlabeled Ultrasound Video Using 3D Convolutional Neural Networks

A 3-dimensional convolutional neural network is trained on unlabeled ultrasound video to predict an upcoming tongue image from previous ones. The network obtains results superior to those of simpler predictors and provides a starting point for exploiting the higher-level representation of the tongue...

Full description

Saved in:
Bibliographic Details
Main Authors: Wu, Chengrui, Chen, Shicheng, Sheng, Guorui, Roussel, Pierre, Denby, Bruce
Format: Conference Proceeding
Language:English
Subjects:
Convolutional neural networks
Data mining
Linear programming
motion detection
silent speech interface
speech production
Task analysis
Tongue
Training
Ultrasonic imaging
ultrasound
unsupervised learning
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A 3-dimensional convolutional neural network is trained on unlabeled ultrasound video to predict an upcoming tongue image from previous ones. The network obtains results superior to those of simpler predictors and provides a starting point for exploiting the higher-level representation of the tongue learned by the system in a variety of applications in speech research. This work is believed to be the first application of convolutional neural networks to unlabeled ultrasound video for the purpose of predicting tongue movement.
ISSN:2379-190X
DOI:10.1109/ICASSP.2018.8461957