John F. Houde
Michael I. Jordan
Dept. of Brain and Cognit. Sci., MIT, 79 Amherst St., Cambridge, MA 02139
This study investigated the ability of the speech production system to learn to compensate for changes in auditory feedback. The setup used for this was a DSP system that transformed the immediate feedback a subject received when speaking. This system can analyze a subject's speech into a formantlike representation, possibly alter it, and then use it to resynthesize speech which is fed back to the subject with no noticeable delay (16 ms). The first of the experiments investigated whether subjects would learn to compensate for a change in vowel identity when producing CVC words. It was found that compensatory articulations were indeed learned, and that these persisted even when no auditory feedback was provided. The findings suggest similarities between speech and other sensorimotor tasks, such as reaching, which also show such adaptation. Other experiments characterizing the degree to which this effect generalizes across differing word and vowel environments will also be presented.