New Delhi: Scientists said Monday they have found a way to use brain scans and artificial intelligence modeled to transcribe “the gist” of what people are thinking, in what was described as a step towards mind reading.
While the main goal of the speech decoder is to help people who have lost the ability to communicate, the US scientists acknowledged that the technology raised questions about “mental privacy.”
In order to allay such fears, they conducted tests that showed that their decoder could not be used on anyone who had not allowed them to be trained on their decoder. brain activity for long hours inside a functional magnetic resonance imaging scanner (fMRI).
Former investigation has shown that a brain implant can allow people who can no longer speak or type to spell words or even sentences.
These “brain-computer interfaces” focus on the part of the brain that controls the mouth when it tries to form words.
alexander huthneuroscientist at the University of Texas at Austin and co-author of a new study, said his team’s language decoder “works on a very different level.”
“Our system really works at the level of ideas, of semantics, of meaning,” Huth said at an online news conference.
It is the first system capable of reconstructing continuous language without an invasive brain implant, according to the study in the journal Nature Neuroscience.
– ‘Deeper than language’ – For the study, three people spent a total of 16 hours inside an fMRI machine listening to spoken narrative stories, mostly podcasts like The New York Times’ Modern Love.
This allowed the researchers to map how words, phrases and meanings generated responses in brain regions known to process language.
They fed this data into a neural network language model using GPT-1, the predecessor to the AI technology later implemented in the hugely popular ChatGPT.
The model was trained to predict how each person’s brain would respond to perceived speech, then narrowed down the options until it found the closest answer.
To test the accuracy of the model, each participant listened to a new story in the fMRI machine.
The study’s first author, Jerry Tang, said the decoder could “retrieve the essence of what the user was listening to.”
For example, when the participant heard the phrase “I don’t have my driver’s license yet,” the model responded with “She hasn’t even started learning to drive yet.”
The decoder had problems with personal pronouns like “I” or “she,” the researchers admitted.
But even when the participants thought about their own stories or watched silent movies, the decoder was still able to pick up the “gist,” they said.
This showed that “we are decoding something that is deeper than language, and then turning it into language,” Huth said.
Because fMRI is too slow to capture individual words, it collects a “hodgepodge, an agglomeration of information in a few seconds,” Huth said.
“Then we can see how the idea evolves, even if the exact words are lost.”
– Ethical caveat: David Rodríguez-Arias Vailhen, a professor of bioethics at the University of Granada in Spain who was not involved in the research, said it went beyond what had been achieved with previous brain-computer interfaces.
This brings us closer to a future in which machines are “able to read minds and transcribe thought,” he said, warning that this could happen against people’s will, such as when they are sleeping.
The researchers anticipated such concerns.
They did tests that showed that the decoder didn’t work on a person if it hadn’t been trained on their own particular brain activity.
The three participants were also able to easily thwart the decoder.
While listening to one of the podcasts, users were told to count by sevens, name and imagine animals, or tell a different story in their minds. All of these tactics “sabotaged” the decoder, the researchers said.
Next, the team hopes to speed up the process so they can decode the brain scans in real time.
They also called for regulations to protect mental privacy.
“Until now, our mind has been the guardian of our privacy,” said bioethicist Rodríguez-Arias Vailhen.
“This discovery could be a first step in compromising that freedom in the future.”
