The proposed work will provide mathematical and computational techniques for recovering articular movement from speech acoustics. Such techniques would be of value to experimental speech science, where the coordinated movements of the articulators are often the objects of investigation. Such a procedure can provide articulatory information when there is no movement measurement possible, as is the cases encountered outside the laboratory or with young children. Trajectories of acoustic variables, such as the time course of a formant frequency, will be used to map onto trajectories of articulatory variables, such as the time course of jaw angle. The optimization required for the mapping will be performed once over entire trajectories, corresponding to consonant-vowel sequences. This should make the method efficient, as well as unambiguous. The set of articulatory variables will include aerodynamic and laryngeal variables, such as subglottal pressure and vocal fold tension. These variables will help to provide detailed information during obstruent production, and in transitions to or from obstruents. Least-squares optimization procedures based on relations between the articulation and the resulting sound output will be used.
