Wearing an electrode-studded cap bristling with wires, a young man silently reads a sentence in his head. Moments later, a Siri-like voice breaks in, attempting to translate his thoughts into text, \u201cYes, I\u2019d like a bowl of chicken soup, please.\u201d It\u2019s the latest example of computers translating a person\u2019s thoughts into words and sentences.<\/p>\n
Previously, researchers have used implants surgically placed in the brain or bulky, expensive machines to translate brain activity into text. The new approach, presented at this week\u2019s NeurIPS conference by researchers from the University of Technology Sydney, is impressive for its use of a non-invasive EEG cap and the potential to generalize beyond one or two people.<\/p>\n
The team built an AI model called DeWave that\u2019s trained on brain activity and language and linked it up to a large language model\u2014the technology behind ChatGPT\u2014to help convert brain activity into words. In a preprint posted on arXiv, the model beat previous top marks for EEG thought-to-text translation with an accuracy of roughly 40 percent. Chin-Teng Lin, corresponding author on the paper, told MSN they\u2019ve more recently upped the accuracy to 60 percent. The results are still being peer-reviewed.<\/p>\n
Though there\u2019s a long way to go in terms of reliability, it shows progress in non-invasive methods of reading and translating thoughts into language. The team believes their work could give voice to those who can no longer communicate due to injury or disease or be used to direct machines, like walking robots or robotic arms, with thoughts alone.<\/p>\n
Guess What I\u2019m Thinking
\nYou may remember headlines about \u201cmind-reading\u201d machines translating thoughts to text at high speed. That\u2019s because such efforts are hardly new.<\/p>\n
Earlier this year, Stanford researchers described work with a patient, Pat Bennett, who\u2019d lost the ability to speak due to ALS. After implanting four sensors into two parts of her brain and extensive training, Bennett could communicate by having her thoughts converted to text at a speed of 62 words per minute\u2014an improvement on the same team\u2019s 2021 record of 18 words per minute.<\/p>\n