Tongue motion averaging from contour sequences

Abstract

In this paper, a method to get the best representation of a speech motion from several repetitions is presented. Each repetition is a representation of the same speech captured at different times by sequence of ultrasound images and is composed of a set of 2D spatio‐temporal contours. These 2D contours in different repetitions are time aligned first by a shape based Dynamic Programming (DP) method. The best representation of the speech motion is then obtained by averaging the time aligned contours from different repetitions. Procrustes analysis is used to measure the contour similarityin the time alignment process and to get the averaged best representation. To get the point correspondence for Procrustes analysis, a nonrigid point correspondence recovery method based on a local stretching model and a global constraint is developed. Synthetic validations and experiments on real tongue motion are also presented in this paper.

• Motion analysis
• nonrigid motion
• dynamic programming
• time alignment

Acknowledgment

This research was funded in part by NIDCD/NIH grant number R01 DC01758.

Notes

Procrustes was the nickname of a robber who lived on the road from Eleusis to Athens. He offered travelers a room with a bed and he would fit them into the bed by stretching them if they were too short or cutting off their legs if they were too tall (Dryden & Mardia, 1998).