11th Annual Conference of the International Speech Communication Association

Makuhari, Chiba, Japan
September 26-30. 2010

Articulatory Inversion of American English /turnr/ by Conditional Density Modes

Chao Qin, Miguel Á. Carreira-Perpiñán

University of California at Merced, USA

Although many algorithms have been proposed for articulatory inversion, they are often tested on synthetic models, or on real data that shows very small proportions of nonuniqueness. We focus on data from the Wisconsin X-ray microbeam database for the American English textipa{/*r/} displaying multiple, very different articulations (retroflex and bunched). We propose a method based on recovering the set of all possible vocal tract shapes as the modes of a conditional density of articulators given acoustics, and then selecting feasible trajectories from this set. This method accurately recovers the correct textipa{/*r/} shape, while a neural network has errors twice as large.

Full Paper

Bibliographic reference.  Qin, Chao / Carreira-Perpiñán, Miguel Á. (2010): "Articulatory inversion of american English /turnr/ by conditional density modes", In INTERSPEECH-2010, 1998-2001.