University of California neuroscientists and engineers have today described in
Nature their work on a brain-machine interface that can generate
natural-sounding synthetic speech by using brain activity to control a virtual
vocal tract.
It is hoped the work may one day restore the voices of people who have lost
the ability to speak due to paralysis and other forms of neurological damage.
Story and short video here :-
https://www.ucsf.edu/news/2019/04/41...ain-recordings