New AI decoder can convert brain activity into text

Researchers at The University of Texas at Austin have developed a new artificial intelligence system called a semantic decoder that can translate a person's brain activity into text.

The decoder, which relies on a transformer model, has the potential to help individuals who are mentally conscious yet unable to physically speak, such as stroke patients. Unlike other language decoding systems that require surgical implants, this system is noninvasive, measuring brain activity using an fMRI scanner after extensive training of the decoder.

The result is not a word-for-word transcript, but researchers designed it to capture the gist of what is being said or thought. While the system is not yet practical for use outside of the laboratory, the researchers believe it could transfer to other brain-imaging systems in the future.

The study, published in the journal Nature Neuroscience, has addressed concerns about potential misuse of the technology and emphasizes that it should only be used when individuals want to use it and it helps them.