Collaborating Authors

Is this the world's first good robot album?


Benoît Carré has written songs for some of France's biggest stars: from Johnny Halliday – the French Elvis, who died last year – to chanteuse Françoise Hardy. But this month, the 47-year-old is releasing an album with a collaborator he could never have dreamt of working with. It's called Flow Machines, and it is, arguably, the world's most advanced artificially intelligent music program.

AI Song Contest


The 2020 Eurovision Song Contest may have been cancelled, but fans of formulaic pop can still get their fill courtesy of the VPRO AI Song Contest. The contestants and their entries were revealed on 10 April and the public have until 10 May to cast their votes. Thirteen teams have entered, with the competition open to anyone residing in a country eligible to take part in the traditional Eurovision extravaganza. The contestants have used a variety of machine learning techniques to help create their songs, with the teams relying on computer input to different degrees. All artists were keen to stress that, rather than pressing a button and letting their trained algorithms create the entire piece, their work is a result of collaboration between AI and humans.

This Travis Scott Song Was Created By Artificial Intelligence


Digital agency space150 created a deepfake version of Travis Scott named Travisbott, a machine that has produced and released the new song "Jack Park Canny Dope Man," composed through artificial intelligence. The entirely AI-generated song features lyrics and melodies modeled after Scott's music. While the lyrics are absolutely nonsensical, the auto-tuned melodies and backing instrumentals do bear an uncanny resemblance to his sound. The song was achieved by feeding Scott's entire discography into a text generator model over a two week period. In turn, the model was able to mimic the cadence and rhyme schemes that were native and re-occurring in his music.

Generating Long-Term Structure in Songs and Stories


One of the difficult problems in using machine learning to generate sequences, such as melodies, is creating long-term structure. Long-term structure comes very naturally to people, but it's very hard for machines. Basic machine learning systems can generate a short melody that stays in key, but they have trouble generating a longer melody that follows a chord progression, or follows a multi-bar song structure of verses and choruses. Likewise, they can produce a screenplay with grammatically correct sentences, but not one with a compelling plot line. Without long-term structure, the content produced by recurrent neural networks (RNNs) often seems wandering and random.

The XX's Intriguing Intimacy

Mother Jones

After two albums of whispery, painfully fragile pop, the London trio The XX has morphed into a subtly different, though equally intriguing, entity. While I See You still features the creamy melodies and intimate vibes that brought them adoring critics and obsessed fans, these tender introverts display new confidence, embracing insistent R&B-style grooves and tackling unapologetically commercial tunes. Genteel singers Oliver Sim and Romy Madley Croft continue to act out classic boy-girl scenarios of romantic longing and fraught connection, from the anxious uptempo surge of "I Dare You" to the wistful "Test Me," but seem less apologetic and more outgoing (in their shy way). When Croft sighs, "I will be brave for you/Stand on a stage for you/Do the things that I'm afraid to do," she creates the uncanny sensation of eavesdropping on a private real-life encounter.