Dynamic display of vocal tract shape for speech training

Abstract

Children suffering from prelingual hearing impairments have difficulty in speech acquisition due to lack of auditory feedback. They can benefit by speech training aids providing corrective feedback, especially those providing visual feedback of key articulatory efforts. These aids should enable a comparison between the articulatory efforts of the student and that of a teacher or a reference speaker. A system is developed for dynamic display of vocal tract shape to provide visual feedback for production of short voiced utterances. It displays speech waveform, spectrogram, and areagram as validation tools. Intensity, pitch, and vocal tract shape are displayed for use in speech training. LPC analysis of the speech signal is used to estimate the vocal tract shape. Articulatory feedback is provided through 2D mid-sagittal view of the vocal tract, in the form of a variable rate animation emphasizing the place of maximum constriction and the opening at this place. The display has two panels, one for the articulatory efforts of the student and another for that of the teacher, for newly recorded utterances as well as pre-recorded ones.