preprint available: neural network models of the articulatory-acoustic forward mapping

[Christopher Kello]

The following paper may be of interest to some connectionists.  It can
be downloaded at 
http://archlab.gmu.edu/cogdyn/publications
 
Regards,
 
Christopher Kello
Department of Psychology 3F5
George Mason University
Fairfax, VA 22030-4444
 
 
Kello, C. T., & Plaut, D. C. (in press). A neural network model of the
articulatory-acoustic forward mapping trained on recordings of
articulatory parameters. To appear in the Journal of the Acoustical
Society of America.
 
Abstract
 
Three neural network models were trained on the forward mapping from
articulatory positions to acoustic outputs for a single speaker of the
Edinburgh multi-channel articulatory speech database.  The model
parameters (i.e., connection weights) were learned via the
backpropagation of error signals generated by the difference between
acoustic outputs of the models, and their acoustic targets.  Efficacy of
the trained models was assessed by subjecting the models' acoustic
outputs to speech intelligibility tests.  The results of these tests
showed that enough phonetic information was captured by the models to
support rates of word identification as high as 84%, approaching an
identification rate of 92% for the actual target stimuli.  These forward
models could serve as one component of a data-driven articulatory
synthesizer.  The models also provide the first step toward building a
model of spoken word acquisition and phonological development trained on
real speech.