Team Australia wins first Eurovision-inspired AI song contest

Tiếng Việt

Team Australia wins first Eurovision-inspired AI song contest

The song, Beautiful the World, was one of 13 entries in the inaugural AI Song Contest, which was hosted by Dutch radio station VPRO.

The Eurovision-inspired contest invited participating countries to submit a three minute song in the Eurovision style made partly or wholly by artificial intelligence (AI).

Beautiful the World was composed by a team of computer scientists, producers and musicians lead by Sydney production studio Uncanny Valley in collaboration with RMIT University’s Dr Sandra Uitdenbogerd and the University of NSW.

Dr Uitdenbogerd described the song’s sound as “high entropy Daft Punk” and said its creation took on new relevance as the challenging events of 2020 – including catastrophic bushfires in Australia and a global pandemic - unfolded.

“When we started this process we were still reeling from the bushfires,” Dr Uitdenbogerd said.

“So we used our AI processes to turn koala grunts, kookaburra laughs, and tassie devil barks into a kind of instrument, reflecting our concern for all the wildlife dying in the bushfires.

“As the year progressed, [a] coronavirus hit and so we all had to stay at home – many of the lyrics speak to this experience.

“So you can treat it as a bit of fun, but lines such as 'the music of the earth has arrived’ do also give it that serious message of: ‘look after each other, and look after the planet’.”

All these lyrics – along with the melody – were created using a combination of AI processes and human intervention.

Producers from Uncanny Valley used algorithms to turn samples of 200 Eurovision songs – including perhaps the most famous, ABBA’s hit Waterloo – into new melodies.

Lyrics were generated by feeding “seed” words into a computer, which then spat out a series of phrases that were selected by the producers.

Dr Uitdenbogerd’s role was to provide an algorithmic “pattern matching” technique, which can match words and melodies together – a process she refined in her PhD.

The winner was decided by a mix of popular vote and a panel of AI experts, including Vincent Koops (from the Netherlands), Anna Huang (US) and Ed Newton-Rex (UK).

The judges commented on the high quality of the entries.

“Composing a song with AI is hard because you have all the creative challenges that come with song writing, but you also have to juggle with getting the machine learning right.

“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.”