1 week Ago By LAURA UNGAR, Brigid Brown
Scientists have created a device that can convert thoughts about speech into spoken words in real time, similar to the brain chip Elon Musk has been working on . While still in the experimental phase, they hope this brain-computer interface could one day provide a voice for those who are unable to speak. A recent study detailed the testing of this device on a 47-year-old woman with quadriplegia who had been unable to speak for 18 years following a stroke , reports The Associated Press.
As part of a clinical trial, doctors implanted the device in her brain during surgery. The device "converts her intent to speak into fluent sentences," said Gopala Anumanchipalli, a co-author of the study published Monday in the journal Nature Neuroscience. Other brain-computer interfaces, or BCIs, for speech typically experience a slight delay between thoughts of sentences and computerized verbalization.
Such delays can disrupt the natural flow of conversation, potentially leading to miscommunication and frustration, researchers noted. This is "a pretty big advance in our field," said Jonathan Brumberg of the Speech and Applied Neuroscience Lab at the University of Kansas, who was not involved in the study. In California , a team recorded the woman's brain activity using electrodes while she silently spoke sentences in her mind.
The scientists used a synthesizer they built using her voice prior to her injury to create a speech sound that she would have spoken. They trained an AI model to translate neural activity into units of sound. Anumanchipalli, from the University of California, Berkeley, explained that the system operates similarly to current technology used for transcribing meetings or phone calls in real-time.
The innovative implant is strategically placed on the brain's speech center to "listen in," converting those signals into components of speech that form sentences. Anumanchipalli described it as a "streaming approach," where every 80-millisecond segment of speech – roughly half a syllable – is immediately recorded. "It's not waiting for a sentence to finish," he emphasized.
"It's processing it on the fly." Brumberg noted that decoding speech at such speed could match the rapid flow of natural conversation, and the incorporation of voice samples "would be a significant advance in the naturalness of speech." Despite partial funding from the National Institutes of Health, Anumanchipalli assured that the project was not impacted by recent NIH research cuts.
He stated that while further study is necessary, with "sustained investments," this cutting-edge technology might become accessible to patients within the next ten years. Click here to follow the Mirror US on Google News to stay up to date with all the latest news, sports and entertainment stories..
