Masterchannel on why AI Mastering is changing the game: “You get thousands of engineers in one automatic system”
The Scandinavian company’s co-founder, Christian Ringstad Shultz, on the benefits of AI in music.
Image: Getty Images
Norwegian-based AI company Masterchannel has shared its approach to AI mastering on tracks, which flips competing approaches on their heads.
In an interview with MusicTech, the Scandinavian company’s co-founder, Christian Ringstad Shultz, explained that many other companies that use AI to improve mastering “built their tech on huge data sets with millions of songs”.
However, for Masterchannel, who realised that this would result in a lot more work as music trends started to develop over time, they needed something a little but more concrete.
The developers say they worked with thousands of human engineers to achieve “benchmark results” – meaning an objective standard against which the AI’s output can be measured.
Therefore, when a track is uploaded, Shultz explains that the algorithm works in a similar manner to a mastering engineers who would try out different approaches and see which one works best. This means that “Rather than working with one mastering engineer,” says Shultz, “with this approach you get thousands of engineers in one automatic system.”
As a result, the AI can adjust to different styles and trends, and can be “genre-agnostic”, as it is not comparing the music to one set style, but rather, set approaches.
“Normally, you’d have to curate a whole new data set and tailor it for that sound. With Masterchannel, if there’s a new genre, or if we see some errors happening in the output, we can just go back and tweak some of the benchmarks. It makes everything much more flexible.”
In more AI developments, The Grammys have recently set out guidelines for whether songs using artificial intelligence can be nominated.
“At this point, we are going to allow AI music and content to be submitted, but the Grammys will only be allowed to go to human creators who have contributed creatively in the appropriate categories,” says Harvey Mason Jr, CEO of The Recording Academy.
“If there’s an AI voice singing the song or AI instrumentation, we’ll consider it, but in a songwriting-based category, it has to have been written mostly by a human,” he continued.
