A group of Australian producers, data scientists and academics have put their heads together to create a submission for an international artificial intelligence song contest that shares similarities to the recently cancelled Eurovision.
The Australian collective goes by the name Uncanny Valley and is made up of Charlton Hill, Caroline Pegram, Justin Shave, Dr. Oliver Bown, Dr. Alexandra L. Uitdenbogerd, Dr. Brendan Wright and Sally-Ann Williams. Their submission to the contest is called ‘Beautiful the World’ and was created in association with Google’s Creative Lab in Sydney.
Watch the video for ‘Beautiful the World’ below:
‘Beautiful the World’ uses AI algorithms that draw on past Eurovision songs and the sounds of Australian wildlife. The track was inspired by the bushfires that swept through the country, killing more than 1billion animals, and incorporates samples of koalas, kookaburras and Tasmanian devils.
“It is deeply interesting to watch an algorithm discover patterns that underlie music, those which we as experienced listeners find so natural, yet so difficult to describe when prompted,” Wright said in a statement.
Bown explained further, saying the song uses “a system that is designed to try to predict what the next note should be in a musical sequence, given one or more preceding notes”.
“It’s exactly the same concept as trying to predict the closing value of the stock market tomorrow based on the previous week’s values,” he said.
While artificial intelligence is responsible for its melody and lyrics, Uncanny Valley enlisted the help of real-life producers and vocalists to complete the track.
The AI song contest is organised by Dutch broadcaster VPRO and features submissions from Belgium, France, the UK and Germany, among others. Entries were assessed by a panel of judges who work in the AI industry or research. Public voting is open until May 10 and the winner will be announced on May 12.
The 2020 Eurovision Song Contest was cancelled on March 18 due to the coronavirus pandemic.