Skip to main content

AI Brain Decoder Moves Closer to Real-World Use for People With Aphasia

Posted by Marc Airhart on Thursday, February 6, 2025
Brain activity like this, measured in an fMRI machine, can be used to train a brain decoder to decipher what a person is thinking about. In this latest study, UT Austin researchers have developed a method to adapt their brain decoder to new users far faster than the original training, even when the user has difficulty comprehending language.

UT Austin researchers have improved their AI-powered brain decoder, allowing it to translate thoughts into continuous text with just one hour of training—far less than the original 16-hour process. This advancement makes the technology more accessible, particularly for individuals with aphasia, by enabling communication without requiring spoken language comprehension. The team is now collaborating with experts in aphasia research to explore its potential for real-world applications.

News Categories