New ‘Mind Reading’ Technology Turns Thoughts to Speech
Researchers from the University of California, San Francisco have developed tech that will allow entire spoken sentences to be generated based on an individual’s brain activity using !
The device consists of an electrode implant that is placed inside the brain to pick up the electrical signals associated with the movements of the lips, tongue and lower jaw.
A computer system is then used to simulate how these movements form different sounds and to synthesize audible speech through what has been described as a ‘virtual vocal tract.’
The method is a lot easier than scanning the brain for the patterns associated with individual words.
“For the first time, this study demonstrates that we can generate entire spoken sentences based on an individual’s brain activity,” said Professor Edward Chang who worked on the project.
“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.”
Some example speech produced using this process can be heard in the video below.