Neural networks emulate any guitar pedal for $120
1–10 of 160 posts
Re: Neural networks emulate any guitar pedal for $120
#2For context, here is the discussion of a previous iteration of the technology on HN
Re: Neural networks emulate any guitar pedal for $120
#3I'm guessing a Hi-Z input before this contraption could improve the tone and do the pickups of the guitar or bass justice. A dedicated buffer pedal or just a pedal with buffer bypass perhaps?
Re: Neural networks emulate any guitar pedal for $120
#4This is really cool. I wonder if this can be used to simulate pianos, rhodes and wurlitzer sounds.
Re: Neural networks emulate any guitar pedal for $120
#5The video won’t play for me, but does this allow tweaking of parameters? The problem with most projects like this one is that it replicates the sound of a certain pedal with certain settings. That’s a major problem for most guitarists as playing with the knobs live is a big part of the attraction to pedals.
Re: Neural networks emulate any guitar pedal for $120
#6This is really cool. I wonder if this can be used to simulate pianos, rhodes and wurlitzer sounds.
i’ve managed to use the technology in reverse and somewhat successfully undo a effect from audio
Re: Neural networks emulate any guitar pedal for $120
#7any pedal? That seems far-fetched - one trivial counter-example would be a looper as that requires modal input and state. I also wonder if it can handle complex multi-tap delays.
Can anyone give a rough idea of the actual limitations? I would guess that there is a limit to how non-local the effects it can manage are.
Re: Neural networks emulate any guitar pedal for $120
#8The video won’t play for me, but does this allow tweaking of parameters? The problem with most projects like this one is that it replicates the sound of a certain pedal with certain settings. That’s a major problem for most guitarists as playing with the knobs live is a big part of the attraction to pedals.
not quite there yet, but on possibility is train multiple models and switch between them on the fly
another is add more params to the models to take the knob states into the account when doing predictions (which can impact the performance)
Re: Neural networks emulate any guitar pedal for $120
#9any pedal? That seems far-fetched - one trivial counter-example would be a looper as that requires modal input and state. I also wonder if it can handle complex multi-tap delays. Can anyone give a rough idea of the actual limitations? I would guess that there is a limit to how non-local the effects it can manage are.
you could model amplifiers, distortion effects, phasers and flangers, according to CoreAudioML project, which makes this possible
https://github.com/Alec-Wright/CoreAudioML
Re: Neural networks emulate any guitar pedal for $120
#10any pedal? That seems far-fetched - one trivial counter-example would be a looper as that requires modal input and state. I also wonder if it can handle complex multi-tap delays. Can anyone give a rough idea of the actual limitations? I would guess that there is a limit to how non-local the effects it can manage are.
you could model amplifiers, distortion effects, phasers and flangers, according to CoreAudioML project, which makes this possible https://github.com/Alec-Wright/CoreAudioML
You could.. but should you? I appreciate the ingenuity, but tuning this tech is time consuming. I prefer to just carrying on playing my guitar poorly.