Nirvana has influenced every generation of musicians that followed them, but now artificial intelligence has helped take that to the next level. Over The Bridge, a Toronto-based organization that helps folks in the music industry deal with mental illness, has created a new project called Lost Tapes Of The 27 Club, and included is “Drowned In The Sun,” a Nirvana-style song that was made to closely resemble the band’s work with the help of artificial intelligence.
Sean O’Connor, who is on the board of directors at Over The Bridge, explained to Rolling Stone how the instrumental came together, saying, “We took 20 to 30 songs from each of our artists as MIDI files and broke them down to just the hook, solo, vocal melody or rhythm guitar and put those through one at a time. If you put whole songs through, [the program] starts to get really confused on what [it’s] supposed to sound like. But if you just have a bunch of riffs, it’ll put out about five minutes of new AI-written riffs, 90 percent of which is really bad and unlistenable. So you start listening through and just finding little moments that are interesting.”
He also noted that the lyrics were generated with a neural network and said that trial and error was involved with choosing the right generated lyrics for the song.
The singing comes courtesy of Eric Hogan, who fronts the Atlanta Nirvana covers group called Nevermind: The Ultimate Tribute To Nirvana. He said of the experience, “After the conversation, I still didn’t really think it was a real thing, and then they sent me files and money. […] I was like, ‘I don’t know how to [sing] this.’ I had to have the guy who came up with the AI track mumble and hum [the tune]. I would feel weird trying to assume what [Cobain] would do. They had to give me a little bit of a roadmap, and then from there, it was fine.”
Also included on Lost Tapes Of The 27 Club are songs in the style of The Doors, Amy Winehouse, and Jimi Hendrix.
Listen to “Drowned In The Sun” above and check out the Doors, Winehouse, and Hendrix tracks below.
