Will be replaced by Lee AI-mastering is real mastering engineers?
Making music is the most human and human activity in the world, but in recent years artificial intelligence has also begun to play on this field. Algorithms are involved in almost every stage of music production-from creating beats on drum machines to writing the melodies themselves, which can hardly be distinguished from the creations of people. Now AI is starting to work in mastering, and this raises the question of the need to use qualified specialists in one of the most difficult areas of music production.
Mastering is the final step in post-processing audio, and its task is to ensure that the final track sounds balanced regardless of what you listen to it on: even in Spotify, even in iTunes, even on disk. The goal of mastering is to create a whole, coherent musical experience that leads the listener from song to song.The process combines both precise calculation and the personal approach of a mastering engineer. With a good mix, a specialist can easily understand what sound the performer is aiming for and help achieve it. Without mastering, the tracks would be more faded and quiet. Engineer Ian Cooper notes that ” mastering is a bit like photography: you can make the sky bluer and the grass greener.”And mastering can be expensive. Depending on the experience of the engineer, the cost of his services can range from hundreds of dollars to tens of thousands per track — it all depends on the ear and talent of the specialist. For indie artists and sofa musicians, the amount may be unaffordable.
However, in recent years, automatic algorithms have evolved quite seriously and now promise performers access to professional mastering for significantly less money. Some use deep data analysis networks that process incoming data over time, while others are based on a carefully designed human-generated sequence of signals translated into a program format. But despite the different operating principles, their task is the same: to produce a ready-made track after a couple of mouse clicks.
The most popular of these services. You fill in the song, let the Landr algorithm analyze it, and choose from the three suggested options how bright you want the effects to be in it. After that, Landr returns the result. The approach is not the most flexible — if you don’t like the result of Landr, you won’t be able to ask To tweak something, unlike working with a live person.The portal ArsTechnica published a review in 2016, in which it called landr’s auto repair service “autocash”, but others are not so critical and say that the service copes with its tasks). And in theory, with each song processed, the Landr algorithm gets smarter.”In 2017, we conducted a series of blind tests with major labels and professional mastering engineers, and some preferred Landr to larger and better-known mastering studios,” Pascal Pilon, CEO of the service, told the Verge.
Some worry that AI-mastering will take jobs away from live engineers, but London-based engineer Streaky compares it more to buying a costume from a storefront rather than custom-made (see the video below). Those who are interested in fitting the suit to themselves or the quality of the fabric, in any case, will go and order a suit, but for most, a more affordable option is quite acceptable.The developer of iZotope software approached AI from a different point of view. The company already offers a set of plug-ins under the name Ozone, and in 2017 introduced the Master Assistant feature. The assistant does not do all the work for you — it gives you starting points that you can already adjust at your own discretion.
This allows producers to make decisions based on the choices made by the AI. “There is no competition with people,” said a representative of iZotope. ” for professionals, this technology makes it easier to clean the material, which takes a lot of time, and they can concentrate on the creative part.”
MajorDecibel founder Adam Love agrees with this statement: “This is not a substitute for mastering from a mastering engineer. Engineers can give performers feedback, work in a certain style, adjust or highlight some specific points. Man is slow and methodical, but not limited. Automation works faster, but in a much narrower framework.”
So this is just an affordable alternative that will help your music sound better. “We’re not taking jobs or changing the industry, but rather creating a new niche by allowing those who can’t pay for quality mastering to get it,” said Colin McLaughlin, eMastered’s representative. — But for the best mastering, of course, you need to contact a real mastering engineer.”
It’s hard to say if AI will ever learn to listen as hard as a human, but it probably doesn’t need to. Modern AI-mastering is already quite complex and even now is a great option for many musicians.”For those who do not believe that AI can create a competitive sound, I will say that the proof of its work is tens of millions of tracks from artists around the world,” added Pascal Pilon. — I’m sure people had their doubts when automatic cameras were introduced, but no one will argue that they have taken their niche in content creation.”