Scientists have reconstructed Pink Floyd’s Another Brick in the Wall by listening to people’s brain waves
This is reportedly the first time a recognisable song has been decoded from brain activity.
Credit: Getty Images
Scientists have successfully managed to use people’s electrical brain activity to accurately reconstruct the classic Pink Floyd song Another Brick in the Wall.
The experiment – the first time a recognisable song has been decoded from brain activity [per The Guardian] – is hoped to restore the musicality of natural speech in patients who struggle to communicate as a result of neurological conditions like stroke or ALS.
29 patients were played a three-minute segment from Another Brick in the Wall, with the following brain activity recorded using electrodes placed directly on the surface of their brains as they underwent surgery for epilepsy.
AI technology was then used to take the brain scans and turn them into audible material. Though somewhat muffled, the line, “All in all, it’s just another brick in the wall” was heard, with its rhythms and melodies intact.
“It sounds a bit like they’re speaking underwater, but it’s our first shot at this,” says Professor Robert Knight, a neurologist at the University of California in Berkeley who helped conduct the study.
Knight says by using a higher density of electrodes – the team worked with an average separation of 5mm between electrodes – the results of the experiment may improve.
“Now that we know how to do this, I think if we had electrodes that were like a millimetre and a half apart, the sound quality would be much better,” he says.
Staff at the same laboratory have reportedly been able to decipher speech – and even slightly imagined words – from brain scans, but according to Knight, “in general, all of these reconstruction attempts have had a robotic quality”.
“Music, by its very nature, is emotional and prosodic – it has rhythm, stress, accent and intonation,” he continues. “It contains a much bigger spectrum of things than limited phonemes in whatever language, that could add another dimension to an implantable speech decoder.”
