Uncanny Valley, an Australian collective of producers, data scientists and academics, has won an Eurovision-style international artificial intelligence song contest.
The collective shared their now-winning entry ‘Beautiful the World’, last month. The song used AI algorithms that drew on past Eurovision songs and the sounds of Australian wildlife, and was inspired in large part by the bushfires that swept through the country last summer.
The AI song contest was organised by Dutch broadcaster VPRO and featured submissions from Belgium, France, the UK and Germany, among others.
The winner was determined by adding up the points awarded online by the international audience and a panel of AI experts.
Per a press statement from VPRO, the public voted overwhelmingly for ‘Beautiful the World’. The panel, composed of Vincent Koops (from the Netherlands), Anna Huang (US) and Ed Newton-Rex (UK), also rated the track highly, however they gave the German team Dadabots x Portrait XO the full douze points (12).
The panel were “amazed by the teams’ wide range of innovative approaches to using artificial intelligence in creating songs”.
“Composing a song with AI is hard because you have all the creative challenges that come with songwriting, but you also have to juggle with getting the machine learning right,” they said.
“They not only pushed the boundaries of their personal creativity, but also gave the audience a look into the exciting future of human-AI musical collaboration.”
Competition initiator Karen van Dijk, who came up with the idea for the competition, added that she thought “some songs would not be out of place in the official Eurovision Song Contest”.
The 2020 Eurovision Song Contest was cancelled on March 18 due to the coronavirus pandemic.