mySoftware [Updates]

Once you create a user profile on Motifator and update with the appropriate information, the updates shown here will be specific to you.

rssFeeds [Syndicate]


forumforum
 

Old Motifator threads are available in the Archive.

Viewing topic "New, Free AI Software Can Split Audio Into Separate Instruments"

     
Posted on: November 19, 2019 @ 08:04 PM
Michael Trigoboff
Avatar
Total Posts:  642
Joined  09-05-2011
status: Guru

A few weeks ago, a company named Deezer released spleeter: free, open-source artificial intelligence-based software that can split an audio recording of a band into separate instruments, including vocals.

Here is their press release.

You need a relatively modern computer, with an Intel chip that supports some version of AVX.

If your computer doesn’t support the required features, there is a free, online web-based version of spleeter you can try.

I managed to get it installed on one of my computers. It’s not easily done, but I can give more details of how to do it if anyone is interested.

I’ve attached an example of what it can do. I had it extract the vocals of Bob Dylan singing Leopard Skin Pillbox Hat.

File Attachments
leopardskin_vocals.mp3  (File Size: 771KB - Downloads: 49)
  [ Ignore ]  

Posted on: November 19, 2019 @ 11:11 PM
cmayhle
Total Posts:  3102
Joined  10-05-2011
status: Guru

That is very fascinating Michael Trigoboff!

Thank you for sharing the link and example.

  [ Ignore ]  

Posted on: November 20, 2019 @ 03:44 AM
5pinDIN
Avatar
Total Posts:  11155
Joined  09-16-2010
status: Legend
Michael Trigoboff - 19 November 2019 08:04 PM

A few weeks ago, a company named Deezer released spleeter: free, open-source artificial intelligence-based software that can split an audio recording of a band into separate instruments, including vocals.

[...]

I’ve attached an example of what it can do. I had it extract the vocals of Bob Dylan singing Leopard Skin Pillbox Hat.

Impressive - thanks for posting.

  [ Ignore ]