Future Sounds
What if playing with music was as easy as an Instagram filter?
When I’m not writing stories about errant robots and lonely people, I work on software that uses artificial intelligence to separate recordings into their component parts.
You: “That sounds very niche!”
The basic idea is, if you can separate sound into its different sources, you can do a lot of interesting things with those sounds. You can get rid of the vocals of your favorite song, so that you can karaoke to it, or isolate one part of the song so that you can remix it with a new beat. You can isolate the speech in a video and then transcribe or translate it, or create a surround sound mix where it seems like the sounds are playing in different locations.
You: “Blah blah blah. I can’t do any of those things. I’m not an audio engineer.”
Yes, but soon you—regular person who last week turned your face into a talking squirrel on TikTok, and transformed your poorly lit beach vacation photo into a masterpiece with an Instagram filter—you will be able to do a lot of cool things with audio, without needing to have any professional skills.
That’s what we were invited to present on at the recent CODE conference. It’s full of fun demos of how we will edit and play with audio with the same ease as we do today with images and video on TikTok, YouTube, Canva, etc.
And the best part: at the end we’re joined by Keith Shocklee, one of the founding members of Public Enemy and The Bomb Squad, where we talk through the making of the iconic “Fight the Power”--which began with a simple bass and drum beat from James Brown.
So there you go. Now I have a video that explains what we do!
P.S. If you’re just here for the robot stories, I have a new one, “Leisure World,” which just came out in Orca (sadly, in print only, though you could support a great lit mag and buy a PDF for $4). It’s a companion piece to the story VICE published this summer, “An Arctic Cruiselish.”