A system that records the brain’s electrical activity through the scalp can turn thoughts into words with help from a large language model – but the results are far from perfect
Using only a sensor-filled helmet combined with artificial intelligence, scientists have announced they can turn a person’s thoughts into written words.
In the study, participants read passages of text while wearing a cap that recorded electrical brain activity through their scalp. These electroencephalogram (EEG) recordings were then converted into text using an AI model called DeWave.
Chin-Teng Lin at the University of Technology Sydney (UTS), Australia, says the technology is non-invasive, inexpensive, and easily transportable.
While the system is far from perfect, with an accuracy of approximately 40%, Lin says more recent peer-reviewed data shows an improved accuracy exceeding 60%.
In the study presented at the NeurIPS conference in New Orleans, Louisiana, participants read the sentences aloud, even though the DeWave program doesn’t use spoken words. However, participants read the sentences silently in the team’s latest research.
Last year, a team led by Jerry Tang at the University of Texas at Austin reported a similar accuracy in converting thoughts to text. Still, MRI scans were used to interpret brain activity. EEG is more practical, as subjects don’t have to lie still inside a scanner.
