With the new system, 69% of words are properly understood as the scientists continue to research further.
The scientists have found a way to turn brain signals into synthesized speech. They used a novel brain implant that could possibly give voice to people who otherwise cannot speak. This piece of technology is developed by researchers from the University of California, San Francisco. They used their model in five volunteers reading passages from children’s books. Researchers used brain voltages during the storytelling and the patterns were matched to speech. This speech was mostly intelligible albeit unclear in some parts which have raised hopes for researchers to make improvements in the existing model.
One of the most critical parts of this approach was to read the brain’s efforts to control lips, larynx, and jaws that reading thoughts. This gives an edge to the people who have lost the ability to speak can think about forming their mouths to produce words. Josh Chartier who is the co-author of study and UCSF doctoral student says, “We were shocked when we first heard the results – we couldn’t believe our ears. It was incredibly exciting that a lot of the aspects of real speech were present in the output from the synthesizer.”
Although the system is not ready for commercial use, an average of 69% of words can be properly understood, while the researchers focus on stimulating the vocal tract. There will be some time before the implant device like this which artificially generates the voice will speak for those who have lost voice communication ability. Although there is still a long way to go, the breakthrough is encouraging. The paper on the research was published in the journal ‘Nature’.