Brain signals from a 46-year-old man who lost his voice to ALS were decoded using experimental brain implants and translated directly into intelligible speech. A 58-year-old woman, a trained singer, whose voice was gradually silenced by the disease, was able to sing a musical scale. New advances from researchers at the University of California, Davis, to be presented next week at the Society for Neuroscience conference in Washington, demonstrate that research on brain-computer interfaces is moving from proof-of-concept demonstrations to being useful in everyday life. “This system, for the first time, is good enough,” said Cindy Chestek, a biomedical engineer at the University of Michigan. who did not participate in the new job. “Good enough for real communication. It’s good enough to sing.” For years, brain implants combined with increasingly powerful AI have been shown in notable case studies to restore a person’s ability to communicate, ask questions, and even crack jokes. The sense of connection that the technology gave to patients—who had lost control of the muscles that allowed them to speak due to ALS or a stroke—could be profound, but also faltering, because the systems translated the signals first into text and then into speech. A person was trying to speak and electrodes surgically implanted in the brain detected electrical signals. The software would decode those signals into phonemes, the sonic components of words. Participants watched as words appeared, one by one, on a screen, forming a sentence. They would then trigger a cursor click to indicate they were done. Then a computer-generated version of his voice spoke. The research subjects could convey their thoughts in great detail, but with a slight delay, making it difficult to actually join the conversations. People often communicate with the pace, timing, and emphasis of their speech, without composing full responses and mentally pressing “send.” Thank you for your patience while we verify access. If you’re in Reader mode, exit and log in to your Times account or subscribe to all of The Times. Thank you for your patience while we verify access. Already a subscriber? Sign in. Do you want all of The Times? Subscribe.
