Be advised: this thread is not for serious in-depth discussion of weighty topics (we have a link for that), this thread is not for anything Culture War related. This thread is for Fun. You got jokes? Share 'em. You got silly questions? Ask 'em.
- 111
- 1
Jump in the discussion.
No email address required.
Notes -
I have continued to play around with Udio music generation recently, and the stuff it spits out is... disconcertingly high-quality. Its auto-generated lyrics continue to be truly awful, though, so what I do to circumvent having to rely on Udio lyrics or write my own is to ask it to generate a song in Japanese, a language where the insipidness of the lyrics will be lost on me. It absolutely nails the musical aspects of its generations, though; I often like the musical content far more than I do many actual songs.
There's still some artifacting in its generations, but on the compositional level alone it's begun to ape human-created music so well that I think it clearly passes the musical turing test. If it managed to improve the fidelity of its generations and had a lyric generator that wasn't so trash I can see this being a dangerously addictive superstimulus for me. It's easy to fall into states wherein none of the media out there seems to appeal to you, and with generative machine learning the solution to that kind of malaise becomes "just prompt until the prediction machine spits out something you like". It feels utterly solipsistic and also very tempting at the same time.
Here are a number of funk/jazz fusion generations I got over the past couple of days:
https://voca.ro/1kaIduRHpYT1
https://voca.ro/15UbDIfpljpH
https://voca.ro/162be1cbaoaT
Is it just me or are these generations, musically speaking, genuinely really decent? They're still slightly genericised, but no more so than most music out there, and I was not expecting its generation ability to get this good this fast. Despite the fact that I am not an amateur when it comes to music, I like these, and this is something that makes me think that perhaps my music taste has been irreversibly broken.
The first song I consider to be really bad.
The second has a nice bass line that I would be happy to steal wholesale. Much more impressive.
The third one didn't seem any good, either. Sure, it's a simple beat and chord changes, but that's much less impressive than a melody, or funky base line.
Can it output sheet music? Can it output notation? Part of the problem is the synthesizer isn't that great. Ideally it would output notation is something like Frescobaldi.
Can it write a melody for me? Can I give it a melody and have it write counterpoint? While it's interesting to give it words and get out sounds, I'm more interested in including music (notation) and getting music (notation) back.
Different strokes I guess. I'm also not primarily evaluating if the exhibited technical/music theory prowess of the songs in question are particularly impressive - most music isn't particularly rich in complex composition, and mediocre music is inevitably going to represent a large part of Udio's dataset. I consider all of the linked songs to be about on par with a lot of the music that gets released. Instead, I’m evaluating on the basis of “could this be a song that I’d hear out in the wild?”
Ideally, that'd be the goal of a machine learning-driven plugin. Unfortunately I'm not aware of any notation-producing ones worth their salt yet, but I do know that there are a number of very competent plugins which have focused on the generation of sound design.
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link