A brain implant and virtual vocal tract able to produce synthetic speech could give a voice to people who have lost their own.
Created by a team from the University of California, the system does not read the patient’s thoughts. Rather, it was developed by identifying the brain activity associated with the vocal movements used to produce the sounds of words. Using that data, the team then constructed a synthetic vocal tract able to recreate the sounds and speak them aloud, based on the brain patterns of the patient.
According to Edward Chang, professor of neurological surgery, “This is an exhilarating proof of principle that with technology that is already within reach, we should be able to build a device that is clinically viable in patients with speech loss.”