Slightly off-topic. Now that 1920s jazz music is falling into public domain, has anyone tried to reinvigorate the music using AI and generative adversarial approaches? Pre-1940s music didn't have high-fidelity sound, so the strong bass lines weren't captured. In theory, we could "downgrade" modern recordings to sound like 1920s recordings, then use adversarial techniques to train the machine on how to restore the antique recordings. Anyone know of any work being done in this area?
How to Train a Gen AI Kick Drum Model on Your Old Linux Desktop with 6GB VRAM
41–50 of 93 posts
Re: How to Train a Gen AI Kick Drum Model on Your Old Linux Desktop with 6GB VRAM
#42I just wish it had samples! I want to hear it
For sure! I just added a couple
Not sure if there's something wrong with the player, or if it's just me, but they both sound like noise. I guess the first sounds vaguely kick drum-like (but distorted), the second is just noise.
Chrome 149.0.7827.200 (Official Build) (arm64), macOS Tahoe 26.0.1
Re: How to Train a Gen AI Kick Drum Model on Your Old Linux Desktop with 6GB VRAM
#43Earlier quoted context omitted.
For me creating the exact sound is not very interesting from sound designing perspective. You can always sample the real instrument. Like physical modeling synthesis, the interesting part is to compress the sound to some parameters that you can tweak and generate new sounds Another approach is VAE, which also you give your some latent embedding, you can tweak the embedding to generate new sound. However the meaning o…
"You can always sample the real instrument." This doesn't really work on instruments like guitars. Open D sounds way different than fretted D on the E string. Timbre changes with position and it's one of the ways I determine where a player's hands are on the neck when I'm trying to play their song.
I'm not doing fancy AI stuff but I have worked a lot with my own bespoke supercollider system where I record whole fretboards of guitars and then play alternative notes based off of certain rules. For whatever dumb reason though, the most natural sounding thing is really just playing, e.g., any random D4 from its possibilities at any given moment.
Timbral differences also exist depending on force, the manner plucked, the already ringing overtones... It's hard to know what you want, but the most natural thing is always going to be some organic variation in the notes in general.
If you have a good ear, you aren't, I don't think, hearing so much the timbral diff in the individual open or fretted notes as much as the fact that a barre chord and an open chord is a different voicing of the same harmony.
Re: How to Train a Gen AI Kick Drum Model on Your Old Linux Desktop with 6GB VRAM
#44Confused. Why not just make the kick drum from a sine? Seconds
I sound design a lot of stuff (in fact I made some of the default kicks in the app), but this is just a different tool, and I wanted some practice training and deploying a generative AI model.
Re: How to Train a Gen AI Kick Drum Model on Your Old Linux Desktop with 6GB VRAM
#45This has been done years ago. See https://audialab.com/products/emergent-drums-2/ for instance.
Interesting! I had not seen this. On their website they mention diffusion but not the other models so it might not be identical but its definitely similar.
Re: How to Train a Gen AI Kick Drum Model on Your Old Linux Desktop with 6GB VRAM
#46Slightly off-topic. Now that 1920s jazz music is falling into public domain, has anyone tried to reinvigorate the music using AI and generative adversarial approaches? Pre-1940s music didn't have high-fidelity sound, so the strong bass lines weren't captured. In theory, we could "downgrade" modern recordings to sound like 1920s recordings, then use adversarial techniques to train the machine on how to restore the ant…
So the idea would be to reconstruct the low frequency components from whatever upper harmonics are left in the recording? If you know the instruments and positioning of the recording device and something of its(the instruments, recorder, environment, etc.) characteristics, it might be possible to solve that using classic methods. There would be huge numbers of parameters, it is an interesting thought. Is there a large easily/freely available corpus of those recordings?
Re: How to Train a Gen AI Kick Drum Model on Your Old Linux Desktop with 6GB VRAM
#47Slightly off-topic. Now that 1920s jazz music is falling into public domain, has anyone tried to reinvigorate the music using AI and generative adversarial approaches? Pre-1940s music didn't have high-fidelity sound, so the strong bass lines weren't captured. In theory, we could "downgrade" modern recordings to sound like 1920s recordings, then use adversarial techniques to train the machine on how to restore the ant…
To do this, I think you are right that you would need to 'downgrade' modern recordings to sound old so that you have both sides of the training data covered.
This would be a cool project to work on. Ideally you would buy some vintage gear and then run the audio through both, but that would be very expensive. You could may be find some vst emulations though and get decent results.
Re: How to Train a Gen AI Kick Drum Model on Your Old Linux Desktop with 6GB VRAM
#48You could save so much time and processing power by just learning how to sidechain.
Re: How to Train a Gen AI Kick Drum Model on Your Old Linux Desktop with 6GB VRAM
#49Confused. Why not just make the kick drum from a sine? Seconds
A sine is only a part of most kicks
Re: How to Train a Gen AI Kick Drum Model on Your Old Linux Desktop with 6GB VRAM
#50Earlier quoted context omitted.
"You can always sample the real instrument." This doesn't really work on instruments like guitars. Open D sounds way different than fretted D on the E string. Timbre changes with position and it's one of the ways I determine where a player's hands are on the neck when I'm trying to play their song.
I'm not doing fancy AI stuff but I have worked a lot with my own bespoke supercollider system where I record whole fretboards of guitars and then play alternative notes based off of certain rules. For whatever dumb reason though, the most natural sounding thing is really just playing, e.g., any random D4 from its possibilities at any given moment. Timbral differences also exist depending on force, the manner plucked,…
No, I'm going off the timbral differences - same way I identify which pickup position is being used. There's a specific 'thickness' I cue in on to determine pickup and specific note placement.