Making music is one of the most humane things we do, but in recent years, artificial intelligence has stepped in to lend a hand in the process. Algorithms have crept into almost every part of the music creation process, from generating original drum loops to writing melodies, producing parts that are increasingly difficult to distinguish from those played by humans. Now, artificial intelligence is coming into the mastering process, raising complex questions about the need for human expertise in the more specialized areas of music production .
Will artificial intelligence replace humans?
Mastering is the final step in audio post-production and balances all the elements of a song so it sounds consistent no matter how you listen to it – on Spotify, iTunes, or on CD. The goal of mastering is to make the listening experience balanced and there is cohesion between each of the songs. The process is a mixture of science and personal taste. With a good mix, a mastering engineer will make sure they understand the sound you’re looking for and help you achieve it. Without mastering, the song will be quieter and less punchy. As experts in the field say, mastering is a bit like photography: you can make the sky bluer, the greens greener, and so on.
Mastering can also be expensive . Depending on the experience of the engineer, a single song can cost anywhere from hundreds to tens of thousands of euros, thanks to the critical listening skills involved. Those prices can be totally prohibitive for independent artists and producers, who are a long way from being able to spend those figures on the production of their work.
Professional work at the click of a button
However, in recent years, automated options have appeared that promise artists access to professional-sounding mastering without the expense of hiring human music engineers . Some use deep learning networks, which analyze the data fed to them over time, while others use a carefully crafted chain of signals, designed by a human and implemented as software. But no matter how they operate, the goal is the same: dominate the audio with a couple of clicks.
Landr is one of the most popular services, hosted as a web service. You can load the song you want to master, let Landr’s algorithm analyze it, choose from three options on how strongly you want the effects to be applied, and then export the result. It’s a general approach and not exactly flexible. If you’re not happy with what Landr has to offer, you can’t ask Landr to improve the sound like you would a human engineer. Music magazine ArsTechnica published a scathing review of this software back in 2016, when the technology was still very much in its infancy.
