Tech that can tell which song you are listening to
A mind-reading technique has ability to decode a person’s playlist; this tech could help us communicate with locked-in syndrome patients
Scientists have developed a new technique that can ‘read’ your mind and identify the songs you are listening to. The technique, developed by researchers at D’Or Institute for Research and Education in Brazil and University Hospital Leipzig in Germany, paves the way to new research on reconstruction of auditory imagination and inner speech.
It can also enhance braincomputer interfaces in order to establish communication with locked-in syndrome patients. In the experiment, six volunteers heard 40 pieces of classical music, rock, pop, jazz, and others. The neural fingerprint of each song on participants’ brain was captured by the MRI machine while a computer was learning to identify the brain patterns elicited by each musical piece. Musical features such as tonality, dynamics, rhythm and timbre were taken in account by the computer. After that, researchers expected that the computer would be able to do the opposite way: identify which song participants were listening to, based on their brain activity – a technique known as brain decoding.
When confronted with two options, the computer showed up to 85 per cent accuracy in identifying the correct song, which is a great performance, comparing to previous studies. Researchers then pushed the test even harder by providing not two but 10 options to the computer.
In this scenario, the computer correctly identified the song in 74 per cent of the decisions. In the future, studies on brain decoding and machine learning will create possibilities of communication regardless any kind of written or spoken language.
“Machines will be able to translate our musical thoughts into songs,” said Sebastian Hoefle, researcher from D’Or Institute. According to Hoefle, brain decoding researches provide alternatives to understand neural functioning and interact with it using artificial intelligence.