Scientists have developed a device that can translate thoughts on discourse into spoken words in real time.
Although it is still experimental, they hope that the cerebral computer interface can one day give voice to those who cannot speak.
A new study described trying the device in a 47 -year -old woman who could not speak for 18 years after a stroke. Doctors implanted it in their brain during surgery as part of a clinical trial.
“He turns his intention to speak into sentences fluently,” said GoPala Anumanchipalli, co -author of the study published Monday in the journal Nature Neuroscience.
Other brain interfaces, or BCI, for speech they generally have a slight delay between prayer thoughts and computerized verbalization. Such delays can interrupt the natural flow of conversation, which can lead to lack of communication and frustration, the researchers said.
This is “a fairly large advance in our field,” said Jonathan Bumberg, of the speech and applied the neuroscience laboratory at the University of Kansas, which was not part of the study.
A team in California registered the brain activity of women using electrodes while spoke sentences in his brain. The scientists used a synthesizer who built using their voice before their injury to create a speech sound that would have spoken. They trained an AI model that translates neuronal activity into sound units.
It works similar to the existing systems used to transcribe meetings or telephone calls in real time, said Anumanchipalli, from the University of California, Berkeley.
The implant itself is located in the center of the brain to be listening to, and those signs translate to pieces of discourse that make up sentences. It is a “transmission approach,” said Anumanchipalli, with each piece of speech of 80 milliseconds, approximately half a syllable, sent to a recorder.
“He is not waiting for a prayer to end,” said Anumanchipalli. “He is processing it on the fly.”
The decoding speech that quickly has the potential to keep up with the rapid rhythm of natural discourse, Bumberg said. The use of voice samples, he added, “would be a significant advance in the naturalness of speech.”
Although the work was partially funded by the National Health Institutes, Anumanchipalli said it was not affected by the recent NIH research cuts. More research is needed before technology is ready for broad use, but with “sustained investments”, it could be available for patients within a decade, he said.
