9th Annual Conference of the International Speech Communication Association

Brisbane, Australia
September 22-26, 2008

Predicting Tongue Shapes from a Few Landmark Locations

Chao Qin (1), Miguel A. Carreira-Perpinan (1), Korin Richmond (2), Alan Wrench (3), Steve Renals (2)

(1) University of California at Merced, USA
(2) University of Edinburgh, UK; (3) Queen Margaret University, UK

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 mm error per point on the tongue.

Full Paper

Bibliographic reference.  Qin, Chao / Carreira-Perpinan, Miguel A. / Richmond, Korin / Wrench, Alan / Renals, Steve (2008): "Predicting tongue shapes from a few landmark locations", In INTERSPEECH-2008, 2306-2309.