An experimental brain implant has shown the ability to decode both speech and gestures at the same time in people with severe paralysis, according to a study published in the journal Nature Neuroscience on September 14. This research, led by scientists at the University of California, San Francisco (UCSF), highlights the potential of brain-computer interfaces (BCIs) to allow more natural forms of communication by integrating multiple ways of expressing thoughts. The study involved three individuals with paralysis who had high-density electrocorticography (ECoG) implants, a technique that records electrical signals directly from the brain's surface using electrodes placed on the cortex. These implants enabled the system to detect brain activity related to both speech-related movements—like those of the mouth and face—and upper limb gestures.
To test the system, researchers developed a real-time interface that could decode both speech and gestures simultaneously and display them on a full-body digital avatar. Participants were asked to perform specific gestures, answer conversational questions, or do both at the same time. In two of the participants, the system successfully decoded both speech and gestures during conversational tasks. One participant achieved a median accuracy of 100% on three conversation blocks, showing the system’s ability to handle complex, real-world interactions. The researchers found that training the system with both isolated and simultaneous data improved its performance across various situations, making it more adaptable to different communication needs.
While the results are promising, the researchers caution that more testing is needed before this technology can be widely used. They plan to evaluate the system with a larger group of participants and a broader range of words and gestures to ensure its reliability and effectiveness in diverse scenarios. The study emphasizes that the findings represent a significant step toward creating brain-computer interfaces that can support more natural and fluid communication for individuals with paralysis. This could ultimately help them express themselves more freely and interact with the world in ways that are closer to typical human communication.
Experimental Brain Implant Decodes Speech and Gestures in Paralyzed Individuals
AI-rewritten from original reportingHow it works
brain-implantparalysisneurosciencecommunicationecogtechnology



