York academic to represent UK in AI Eurovision Song Contest

After the Eurovision Song Contest was cancelled, the Dutch public broadcaster decided to host a virtual one instead

An academic from the University of York is the brains behind the UK’s entry to this year’s artificial intelligence (AI) Eurovision Song Contest.

The traditional Eurovision Song Contest, which was set to be hosted by The Netherlands, was postponed because of the coronavirus outbreak – the first time in its 64-year history the competition has not gone ahead.

In the camp-filled contest’s stead, Dutch public broadcaster VPRO has decided to host a virtual contest with AI-composed music.

Dr Tom Collins, from the University of York’s department of music, and his spouse, Dr Nancy Carlisle, from Lehigh University, USA, wrote and recorded the UK’s entry – a ballad called Hope Rose High.

The song was composed by an algorithm written by Dr Collins, which generates new material in the style of an existing corpus of music.

Rather than pitting man against machine, I hope this contest will increase public understanding of how AI can increasingly be used as an aid to humans in the creative process as opposed to a replacement
– Dr Tom Collins, University of York

The algorithm analysed data from 200 previous Eurovision entries, and programmed it to generate 30 four-bar melodies, chord progressions, basslines and drumbeats.

Dr Carlisle then paired them with melodies, before Dr Collins arranged the song.

Dr Tom Collins said: “The song and video have all come together in a bit of a hurry while my family and I are on lockdown through the Covid-19 outbreak.

“Rather than pitting man against machine, I hope this contest will increase public understanding of how AI can increasingly be used as an aid to humans in the creative process as opposed to a replacement.

“I think we will see the use of AI increasingly in the music scene. In creative industries many people struggle with the ‘blank page’ problem, where creativity is stifled by having too many options. AI can help by providing stylistically appropriate jumping off points.”

A total of 13 teams from Australia, Sweden, Belgium, the UK, France, Germany, Switzerland and the Netherlands are competing.

Voting opens today (Friday 10 April) and a panel of AI experts will help judge the songs.


You might also like: University of East Anglia (UEA) partners with Rathbones Folio Prize


 

Leave a Reply

Send an Invite...

Would you like to share this event with your friends and colleagues?

UPCOMING LIVE WEBINAR

Don't let your edtech tools use you

How to ensure pedagogy comes before technology

JOIN FOR FREE 3 March 2021, 11am [GMT]