Predicting Tongue Shapes from a Few Landmark Locations
View/ Open
Date
2008-09Author
Qin, Chao
Carreira-Perpinan, Miguel A.
Richmond, Korin
Wrench, Alan A.
Renals, Steve
Metadata
Show full item recordCitation
Qin, C., Carreira-Perpinan, M., Richmond, K., Wrench, A. & Renals, S. (2008) Predicting Tongue Shapes from a Few Landmark Locations, Proceedings of Interspeech, Brisbane, pp. 2306-2309.
Abstract
We present a method for predicting the midsagittal tongue contour from the locations of a few landmarks (metal pellets) on the tongue surface, as used in articulatory databases such as MOCHA and the Wisconsin XRDB. Our method learns a mapping using ground-truth tongue contours derived from ultrasound data and drastically improves over spline interpolation. We also determine the optimal locations of the landmarks, and the number of landmarks required to achieve a desired prediction error: 3-4 landmarks are enough to achieve 0.3-0.2 mm error per point on the tongue.