HACKER Q&A
📣 zora_goron

Anyone have information about the ML used in recent Beatles' remasters?


I've come across several articles discussing the role of Machine Learning in remastering Beatles' tracks, both from the "Get Back" documentary [0] as well as the upcoming "Revolver" album remix [1]. Does anyone have any additional knowledge about the software or type of models used for this sort of task?

[0] https://www.openculture.com/2021/12/how-peter-jackson-used-artificial-intelligence-to-restore-the-video-audio-featured-in-the-beatles-get-back.html

[1] https://www.salon.com/2022/09/15/remixed-revolver-to-reveal-new-layers-of-the-beatles-extraordinary-musical-powers/

  👤 ZeroGravitas Accepted Answer ✓
I don't know about Peter Jackson specifically but the seperating of different instruments and vocals is a fairly common task, as lots of famous music was recorded on a limited number of tracks, and seperating them out is a part of most modern remixes.

I believe there's a couple of open source tools for this, but not sure how they compare with state of the art.

edit: article introducing one of them https://tech.fb.com/artificial-intelligence/2020/03/one-trac...