The "problem" is copyright, the music industry has way more power than the people that were copyright infringed by Stable Diffusion et al. And probably no artist that makes a living from their music will voluntarely give his music to AI.
Re:MusicLM: Generating music from text
by makingstuffs on Friday January 27, 2023 @03:26AM
(#34543890)
They should be able to get a significant amount of royalty free music. Granted it will generally be of a lower quality and/or be older but it should still be more than significant.
Pirates will gladly provide that content to the AI. Look what's happening with deepfakes.
are there upscalers in the wavenet world like there are in convnets?
This is the best music that incorporates AI that I have heard by a long shot - process is here:
https://ooo.ghostbows.ooo/about/
Music is on all the usual streaming platforms, the album is called Shadow Planet, band is The Cotton Modules. Also avail on their website:
They really need to bump up to 48 KHz so all the music doesn't sound like it's being played over a telephone. A factor of two in the cost of generation shouldn't be prohibitive. So much of the audio generation stuff I've seen has a fatal flaw like this baked into the dataset and/or generation process that ensures the output can't sound good even in theory, it's kinda frustrating.
It's also frustrating that nobody AFAIK has trained an audio model on an actually large music dataset. We're training GPT-3 on a significant fraction of the text of the whole internet! Where are the audio models trained on a significant fraction of all recorded music?