Aussie team to compete in Eurovision-style song contest

A team of local music producers, data scientists and academics are making music together.

The team, all members of music-tech collective Uncanny Valley, will compete against other teams from across Europe for the best new Eurovision-like hit created with AI.

The AI-created song, ‘Beautiful the World’, uses artificial intelligence algorithms trained on past Eurovision songs and local wildlife to give it a uniquely Aussie sound.

The competition, organised by ​Dutch public broadcaster VPRO, will be judged by a panel of experts, with the global public encouraged to vote online to influence the outcome.

The Australian entry was inspired by the bushfires that devastated the country earlier this year taking the lives of many native animals.

The song uses audio samples of koalas, kookaburras and Tasmanian devils, and its message is one of hope – that nature will not only recover but triumph, the team said.

“The AI Song Contest is a really interesting prize because it supports transparency of process, innovation and open discussion,” said team member Dr Oliver Bown, who specialises in creative applications of artificial intelligence at UNSW Art & Design.

Contestants provide details about their creative systems and processes, and this encourages knowledge sharing and for the systems to be objectively evaluated, he said.

“It can be a problem in this field for people to just say ‘listen to this great music made by machine’ and to let the music alone speak for the quality of the computational system,” he said. “But you never really know what you’re hearing until you’re able to examine the system.”

‘Beautiful the World’ takes a “co-creative approach”, pairing human input with algorithms.

While an artificial intelligence algorithm trained on past Eurovision songs was responsible for the melody and the lyrics, the team used both a producer and vocalists to bring the song to life.

“We like to collaborate and rage with​ the machine​s,” said producer Caroline Pegram.

The team also includes Dr Brendan Wright, a data scientist from UNSW Engineering.

“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,” said Wright. “These algorithms can then generate fundamentally new sound with startling clarity.”

The AI Song Contest is organised by VPRO in collaboration with NPO 3FM and NPO Innovation. The winner will be announced on May 12. To vote, please visit the VPRO Broadcast site.