A New Kind of AI Can Turn Brain Activity into Text

Reading people’s minds might just not be something that you see in a movie, as researchers in the U.K have just bought reading minds a step closer to reality. A newly developed artificial intelligence can turn brain activity into text that was recently unveiled. The current system works on converting the neural patterns as someone is speaking aloud. These kinds of system were initially developed for people suffering from locked-in syndrome.

“We are not there yet but we think this could be the basis of a speech prosthesis,” said Dr. Joseph Makin, co-author of the research from the University of California, San Francisco. The participants were asked to read aloud 50 pre-determined that included “Tine Tuner is a pop singer”, and “Those thieves stole 30 jewels”. The team behind the AI than tracked the neural activities as they were speaking. This data was further fed into a machine-learning algorithm that converted brain activity for each spoken sentence into a specific set of numbers.

To make sure that numbers related to certain aspects of speech, the algorithm compared sounds that were predicted from smaller chunks of brain activity with the actual recorded audio. The string of numbers is then fed into a second part of the system which converts the following data into a sequence of words.

In the beginning, the system just kept out spewing different sentences as the system compared each sequence of words with the sentences that were read aloud incorrectly. Among its mistakes, “Those musicians harmonize marvelously” was decoded as “The spinach was a famous singer”, and “A roll of wire lay near the wall” became “Will robin wear a yellow lily”. However, the team followed suit by generating written text from brain activity during speech.

Dr. Mahnaz Arvaneh, an expert in brain-machine interfaces at Sheffield University urged to consider ethical issues now. “Weare still very, very far away from the point that machines can read our minds. “But it doesn’t mean that we should not think about it and we should not plan about it.”