Ask HN: AI-Generated Music?

78 points by simonebrunozzi ↗ HN
I'd guess that we would be now ready for great, successful AI-generated music. I know nothing about it, of course - can someone more knowledgeable than me tell me what's going on, what's interesting, what's noteworthy in the year 2022?

58 comments

[ 4.4 ms ] story [ 32.4 ms ] thread
There is this: https://www.aiva.ai/

I've toyed around with it a bit. It's impressive for sure, but I am not sure I think of it as anything other than a curiosity.

Same. It's very underwhelming for now.
Yes. I feel like they made zero progress since they launched as far as the actual quality of the music. They added a bunch of product features but not things that matter. Melody and harmony have not improved (still takes ~50 tries to generate something that doesn’t sound mediocre or outright bad.
Not entirely AI-generated, but one of the two folks on this project used an AI music generator (called "Jukebox", IIRC, but it's not on the page) to generate snippets based on the other's musical ideas, and then the two collaborators worked with those to build songs.

Some nice results, here's the "About" page that describes their process:

https://ooo.ghostbows.ooo/about/

----

Edit: Here's where Robin Sloan mentions Jukebox:

https://www.robinsloan.com/lab/notes-on-a-genre/

Yes, it's Jukebox but it's a strange way to try to get an impression of Jukebox because it's simultaneously heavily edited by them but also leaning heavily into the distortions & artifacts. The sample website would be a much better way to hear Jukebox per se: https://jukebox.openai.com/
https://www.ampermusic.com/ Amper music, owned by Shutterstock, has been around for a while. It was quite nice to play around with when it was still free, not sure if, and how it has evolved over the past years.
Do you think there will be Jukebox2, and similar level of improvement as what we saw with GPT->GPT2->GPT3 progression?
Undoubtedly. It’s just a matter of time.

Whether it’ll be OpenAI or someone else is a tossup though. There’s not much commercial incentive to make AI music. So my money is on the hackers. Intellectual curiosity is still one of the most powerful forces of change.

The resources are there. You can get a couple hundred TPUs from google for free. So it’s a matter of talent, not permission.

> You can get a couple hundred TPUs from Google for free

How?

TRC (tpu research cloud). Apply and you’ll almost certainly be accepted. Yes, you.
The first step is AI-assisted music, really. And that's a great and useful niche. Think auto accompaniment, backing tracks, etc. Tools for helping figure out transitions. Someone already pointed out magenta which is a great starting point.
https://www.musicdevelopments.com/

Technically not ‘AI’ though, more based on music theory ‘rules’.

It is not really clear from those pages how RapidComposer works - but it seems it's still AI (the only condition is that you call melodies etc. "solutions").

Of course there exists rule-based AI. Whatever works to partially replace a human professional.

One thing that's been pretty interesting is AI vocal splitting, which has revolutionized the art of remixing music that couldn't be fully remixed before.

I used it to remix one of my favorite songs ever by Biz Markie just before he passed last year. It ended up being the last remix made of his music before his passing, and I sent it to his manager just before, so I'd like to believe he heard it.

It still has a ways to go (as audio quality can be spotty and incomplete), but these online services can often separate more than just vocals now, they can cut individual instruments out of music, and even create pretty good instrumentals. I have been able to remove uncleared vocals from fully mixed tunes that I've made so they can be released as well. I never thought it would have been possible 20 years ago when I started music. As for AI generated music, I think it will be a travesty to de-value or remove humans from the music/art making process entirely, it will always likely be something derivative of human work in essence anyway, but I don't think it will ever match the depth and soul of human-generated music to people who truly know and love music, some things just can't be emulated.

Here's the remix video - https://www.youtube.com/watch?v=xL14JH5f-qM

which service/software did you use for splitting?