The Metacreation Lab’s Spring 2021 newsletter (received via email) features a number of events either currently taking place or about to take place.
2021 marks the 2nd year for this international event, an artificial intelligence/AI Song Contest 2021. The folks at Simon Fraser University’s (SFU) Metacreation Lab have an entry for the 2021 event, A song about the weekend (and you can do whatever you want). Should you click on the song entry, you will find an audio file, a survey/vote consisting of four questions and, if you keep scrolling down, more information about the creative, team, the song and more,
Driven by collaborations involving scientists, experts in artificial intelligence, cognitive sciences, designers, and artists, the Metacreation Lab for Creative AI is at the forefront of the development of generative systems, whether these are embedded in interactive experiences or automating workflows integrated into cutting-edge creative software.
Cale Plut (Composer and musician) is a PhD Student in the Metacreation lab, researching AI music applications in video games.
Philippe Pasquier (Producer and supervisor) is an Associate Professor, and leads the Metacreation Lab.
Jeff Ens (AI programmer) is a PhD Candidate in the Metacreation lab, researching AI models for music generation.
Renaud Tchemeube (Producer and interaction designer) is a PhD Student in the Metacreation Lab, researching interaction software design for creativity.
Tara Jadidi (Research Assistant) is an undergraduate student at FUM, Iran, working with the Metacreation lab.
Dimiter Zlatkov (Research Assistant) is an undergraduate student at UBC, working with the Metacreation lab.
ABOUT THE SONG
A song about the weekend (and you can do whatever you want) explores the relationships between AI, humans, labour, and creation in a lighthearted and fun song. It is co-created with the Multi-track Music Machine (MMM).
Through the history of automation and industrialization, the relationship between the labour magnification power of automation and the recipients of the benefits of that magnification have been in contention. While increasing levels of automation are often accompanied by promises of future leisure increases, this rarely materializes for the workers whose labour is multiplied. By primarily using automated methods to create a “fun” song about leisure, we highlight both the promise of AI-human cooperation as well as the disparities in its real-world deployment.
As for the competition itself, here’s more from the FAQs (frequently asked questions),
What is the AI Song Contest?
AI Song Contest is an international creative AI contest. Teams from all over the world try to create a 4-minute pop song with the help of artificial intelligence.
When and where does it take place?
Between June 1, 2021 and July 1, 2021 voting is open for the international public. On July 6 there will be multiple online panel sessions, and the winner of the AI Song Contest 2021 will be announced in an online award ceremony. All sessions on July 6 are organised in collaboration with Wallifornia MusicTech.
How is the winner determined?
Each participating team will be awarded two sets of points: one a public vote by the contest’s international audience, the other the determination of an expert jury.
Anyone can evaluate as many songs as they like: from one, up to all thirty-eight. Every song can be evaluated only once. Even though it won’t count in the grand total, lyrics can be evaluated too; we do like to determine which team wrote the best accoring to the audience.
Can I vote multiple times for the same team?
No, votes are controlled by IP address. So only one of your votes will count.
Is this the first time the contest is organised?
This is the second time the AI Song Contest is organised. The contest was first initiated in 2020 by Dutch public broadcaster VPRO together with NPO Innovation and NPO 3FM. Teams from Europe and Australia tried to create a Eurovision kind of song with the help of AI. Team Uncanny Valley from Australia won the first edition with their song Beautiful the World. The 2021 edition is organised independently.
What is the definition of artificial intelligence in this contest?
Artificial intelligence is a very broad concept. For this contest it will mean that teams can use techniques such as -but not limited to- machine learning, such as deep learning, natural language processing, algorithmic composition or combining rule-based approaches with neural networks for the creation of their songs. Teams can create their own AI tools, or use existing models and algorithms.
What are possible challenges?
Read here about the challenges teams from last year’s contest faced.
As an AI researcher, can I collaborate with musicians?
Yes – this is strongly encouraged!
For the 2020 edition, all songs had to be Eurovision-style. Is that also the intention for 2021 entries?
Last year, the first year the contest was organized, it was indeed all about Eurovision. For this year’s competition, we are trying to expand geographically, culturally, and musically. Teams from all over the world can compete, and songs in all genres can be submitted.
If you’re not familiar with Eurovision-style, you can find a compilation video with brief excerpts from the 26 finalists for Eurovision 2021 here (Bill Young’s May 23, 2021 posting on tellyspotting.kera.org; the video runs under 10 mins.). There’s also the “Eurovision Song Contest: The Story of Fire Saga” 2020 movie starring Rachel McAdams, Will Ferrell, and Dan Stevens. It’s intended as a gentle parody but the style is all there.
ART MACHINES 2: International Symposium on Machine Learning and Art 2021
The symposium, Art Machines 2, started yesterday (June 10, 2021 and runs to June 14, 2021) in Hong Kong and SFU’s Metacreation Lab will be represented (from the Spring 2021 newsletter received via email),
On Sunday, June 13  at 21:45 Hong Kong Standard Time (UTC +8) as part of the Sound Art Paper Session chaired by Ryo Ikeshiro, the Metacreation Lab’s Mahsoo Salimi and Philippe Pasquier will present their paper, Exploiting Swarm Aesthetics in Sound Art. We’ve included a more detailed preview of the paper in this newsletter below.
Concurrent with ART MACHINES 2 is the launch of two exhibitions – Constructing Contexts and System Dreams. Constructing Contexts, curated by Tobias Klein and Rodrigo Guzman-Serrano, will bring together 27 works with unique approaches to the question of contexts as applied by generative adversarial networks. System Dreams highlights work from the latest MFA talent from the School of Creative Media. While the exhibitions take place in Hong Kong, the participating artists and artwork are well documented online.
Liminal Tones: Swarm Aesthetics in Sound Art
Applications of swarm aesthetics in music composition are not new and have already resulted in volumes of complex soundscapes and musical compositions. Using an experimental approach, Mahsoo Salimi and Philippe Pasquier create a series of sound textures know as Liminal Tones (B/ Rain Dream) based on swarming behaviours
Findings of the Liminal Tones project will be presented in papers for the Art Machines 2: International Symposium on Machine Learning (June 10-14 ) and the International Conference on Swarm Intelligence (July 17-21 ).
Talk about Creative AI at the University of British Columbia
This is the last item I’m excerpting from the newsletter. (Should you be curious about what else is listed, you can go to the Metacreation Lab’s contact page and sign up for the newsletter there.) On June 22, 2021 at 2:00 PM PDT, there will be this event,
Creative AI: on the partial or complete automation of creative tasks @ CAIDA
Philippe Pasquier will be giving a talk on creative applications of AI at CAIDA: UBC ICICS Centre for Artificial Intelligence Decision-making and Action. Overviewing the state of the art of computer-assisted creativity and embedded systems and their various applications, the talk will survey the design, deployment, and evaluation of generative systems.
Free registration for the talk is available at the link below.
Remember, if you want to see the rest of the newsletter, you can sign up at the Metacreation Lab’s contact page.