This month, in my Scientific American column, I wrote about the rise of music and art created by artificial intelligence software. What is art’s value when there’s no longer any effort involved in its creation, or scarcity to limit its ownership?
It’s time to start asking these questions, because already, people are using AI software to compose music for them. I thought I’d take a listen to some examples of AI-composed pop songs to see how far along we are.
In this case, researchers fed it Beatles songs—and indeed, the result sounds a little Beatles-ish. Note that FlowComposer produced only a lead sheet (that is, a piece of music showing the melody and chord symbols); a human then arranged it for instruments, wrote lyrics, recorded it, and mixed it. There are some fresh and intriguing chord sequences in this song, but also some noodling, aimless ones that don’t really land.
• “Mr. Shadow.” This song, too, was written by FlowComposer, but this time, it was fed songs by American songwriters Irving Berlin, Duke Ellington, George Gershwin and Cole Porter. The recording is so processed electronically that it’s a little hard to assess the composition itself, but once again, the progressions feel fairly random. Unlike an actual song by one of those composers, this one is unlikely to get stuck in your head.
• “Breaking Free.” YouTube singer Taryn Southern wrote the melody and the lyrics to this pop song, making them fit a track composed, “played,” and mixed by an AI background-music service called Amper Music. The result is much catchier and more harmonically coherent than the Sony entries, no doubt because a human did so much more of the work.
In all of these cases, even the most cutting-edge AI can’t yet compose a decent pop song without human help—the more, the better. But these are just the earliest attempts at AI composing software; the tune may be quite different in a few years.