It might have been our misconception that only humans can create something similar to black metal music, because artificial intelligence has just proved us wrong. A new black metal album has been created and it is definitely not by any human.
From driving cars to printing out food, artificial intelligence is steadily taking over everything. Now, the technology is being used to create a black metal album, which is as fierce as a music generated by humans and it is actually difficult to distinguish if it’s produced by a man or a machine.
The technology is being called as ‘Coditany of Timeness’, a product of a project undertaken by CJ Carr and Zack Zukowski, who go by the name ‘Databots’. The album consists of five tracks that contain songs with algorithmically generated names such as ‘Timension’ and ‘Wisdom Trippin’’. The album cover, too, was created by artificial intelligence.
You can enjoy album below:
Artificial Intelligence to replace humans
The creators explained that generating black metal music is not an easy task. They wrote, “Black metal is characterized by its ultra-long progressive sections, textural rhythms, deep screams, and melodic weaving over a grid of steady, aggressive rhythmic attacks and has extreme characteristics [that] make it an outlier in human music.”
Initially reported by The Outline, the music was generated by setting up the album ‘Diotima’ by the black metal band, Krallice, into an artificial neural network. The songs were then cut down into 3,200 eight-second chunks, where the system was ordered to project how the next part of the song would sound like, before being told if the prediction was right.
According to Carr, initially the sounds produced were ‘grotesque’ and ‘noisy’. They later were renewed to be more refined due to the process that demonstrated over five million guesses in three days at how a metal song should sound like. The end result was 20 sequences, each of four minutes, reported Digital Trends.
“Early in its training, the kinds of sounds it produces are very noisy and grotesque and textural. As it improves its training, you start hearing elements of the original music it was trained on come through more and more,” Carr said.