Computer reads human brain listening to Pink Floyd. Recreates song from reading
Barbara Friedman reports on trending news including the latest research involving scientists who trained a computer to analyse the brain activity of a group of people to recreate a song - creating a leap for sonic-to-speech technology.
(Skip to 5.25 for this one.)
A group of researchers from Berkeley University in California published data on Tuesday (15 August) that revealed how computers can be used to recreate music or sound based on neuronal patterns alone.
To collect the data for the study, the researchers recorded the brains of 29 epilepsy patients at Albany Medical Center in New York State from 2009 to 2015.
As part of their epilepsy treatment, the patients had a net of nail-like electrodes implanted in their brains.
This created a rare opportunity for the neuroscientists to make recordings of their brain activity while they listened to music (Pink Floyd's 1979 hit song "Another Brick in the Wall") - and it worked.
The computer produced a recognisable version of the song based on brain signals.
Listen to what was produced below.
Researchers say that while the audio sounds like it’s being played underwater, it’s a first step toward creating more expressive devices to assist people who can’t speak.
Although artificial intelligence (AI) technologies exist to make speech a reality for those living a life without it, it doesn't always sound natural. This is because a significant amount of the information conveyed through speech comes from what linguists call “prosodic” elements which includes tone.
This means that audio-to-speech technology can be created that doesn't sound robotic because there is room to play with intonation, rhythm and tone.
Friedman says, "this is just an incredible use of technology... that can be life-changing for some."
Read the full study, here.
Scroll up to listen to the full conversation.