On this page
Study design
Researchers recorded sensorimotor-cortex activity with high-density electrocorticography (ECoG) implants in three people with severe paralysis. Decoders translated attempted speech and upper-body gestures into control of a personalized virtual avatar, in isolated and simultaneous tasks.
What the findings show
A single implant provided signals that supported decoding both speech and gestures. Models trained only on isolated behaviors did not transfer as well to simultaneous attempts; including both kinds of trials improved performance across contexts. This is a proof of concept for a brain-computer interface that can represent more than one communication channel at a time.
Limits
The study involved three participants and tested a controlled avatar task, not everyday conversation or a routinely available assistive device. Decoder performance varied with task context and training data. The findings do not establish safety, long-term usability, or benefit for all people with paralysis.
This sourced news summary and translation were prepared with AI assistance. Source links, the news date and research limitations are disclosed; this is not a claim of independent medical expert review. News production method.
Sources
- Simultaneous speech and gesture decoding for multimodal communication in paralysis — Nature Neuroscience ·
Research news is not medical advice or a recommendation to use a substance. Read findings in the context of the study design, participants and limitations. Editorial standards.
← All news