By I. Edwards HealthDay Reporter<\/b>
\n<\/b><\/p>\n
TUESDAY, April 1, 2025 (HealthDay News) — For nearly two decades, a stroke had left a woman unable to speak — until now.<\/p>\n
Thanks to a new brain implant, her thoughts are being turned into real-time speech, giving her a voice again for the first time in 18 years.<\/p>\n
The device was tested on a 47-year-old woman with quadriplegia who lost her ability to speak after a stroke<\/a>. Doctors placed the brain-computer implant during surgery as part of a clinical trial, The Associated Press <\/em>reported.<\/p>\n It \u201cconverts her intent to speak into fluent sentences,\u201d said Gopala Anumanchipalli<\/a>, an assistant professor of electrical engineering and computer sciences at UC Berkeley and a co-author of the study published Monday in the journal Nature Neuroscience<\/a><\/em>.<\/p>\n Unlike other brain-computer systems that have a delay, this new technology works in real time. Scientists say that the delay in existing systems makes conversations hard and, sometimes, frustrating.<\/p>\n Jonathan Brumberg<\/a> of the Speech and Applied Neuroscience Lab at the University of Kansas, who reviewed the findings, welcomed the advances.<\/p>\n This is \u201ca pretty big advance in our field,\u201d he told The Associated Press<\/em>.<\/p>\n Here\u2019s how it works: The team recorded the woman\u2019s brain activity using electrodes as she silently imagined saying sentences.<\/p>\n They also used a synthesizer using her voice before her stroke to recreate the sound she would have made. An AI model was trained to translate her brain signals into sounds.<\/p>\n The system sends each small sound unit — roughly a half-syllable — into a recorder every 80 milliseconds. That means it works quickly, just like real-time transcription on a phone call.<\/p>\n \u201cIt\u2019s not waiting for a sentence to finish,\u201d Anumanchipalli said. \u201cIt\u2019s processing it on the fly.\u201d<\/p>\n Decoding speech that fast could help the device keep up with the speed of natural conversation, Brumberg added. Using a person\u2019s actual voice \u201cwould be a significant advance in the naturalness of speech.\u201d<\/p>\n Though the research was partly funded by the National Institutes of Health, Anumanchipalli said it was not affected by recent cuts<\/a> to NIH funding.<\/p>\n He added that more research is still needed, but with \u201csustained investments,\u201d the device could be available to patients within 10 years.<\/p>\n More information<\/strong><\/p>\n The Stroke Foundation has more on communication after a stroke<\/a>.<\/p>\n