Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Neural networks emulate any guitar pedal for $120

hackaday.com

Post reply on HN
Print view View original

51–60 of 160 posts

Re: Neural networks emulate any guitar pedal for $120

#51

Post by kakwa_ »

montroser wrote: post #33
Applejinx wrote: post #23

…at MP3 quality. This is fine if you like that sort of thing. I would note that latency is very important here: it's not going to be nice to play through if it's incurring any significant latency.

Yes, latency is huge. Modern digital audio stacks in consumer OSes are still completely terrible at this. Not that it's an easy problem to solve. But it's pretty hard to beat elections flowing through an analog circuit, when in the digital side you have to: convert analog to digital, run through the kernel to get to user space, run the bits through the RNN, send back to kernel space, convert to analog and finally sen…

Also we had electronic simulators for various instruments for ages now.

Things like Clavinova keyboards Piano or Line 6 Pods simulating Guitar/Bass amps & effects have been out their for decades now.

And while they have been quite popular due to the sheer number of sonorities and the convenience they bring (possibility to play with an headset, extremely useful to play at night or in apartments), traditional analog setups remain strong.

Playing on an analog setup still is more pleasant and more expressive IMHO, in particular "simulators" tend to mask the attack when hitting a note, and hides a lot the tension/crispation in the hands/fingers when playing, leading to potential bad habits, specially for people learning to play an instrument. Analog to digital and digital to analog conversion definitely lead to loses in expressiveness.

Re: Neural networks emulate any guitar pedal for $120

#52

Post by duped »

marcan_42 wrote: post #24
duped wrote: post #17

Earlier quoted context omitted.

You can model most useful nonlinear functions with neural networks, this is unsurprising. You can also use Volterra series. You can even estimate/measure the Volterra kernel then train a NN to model it instead of dealing with the computational complexity of generalized convolution for nonlinear dynamic systems. The hard part is that there are some fundamental limitations to deal with. The biggest is aliasing - distor…

Now I wonder if a NN would be able to learn a nonlinear effect without aliasing, even if run at the original sample rate. Oversampling and filtering are, after all, things that could become part of the model too. Perhaps it can learn to approximate them with less CPU cost than doing it for real.

Oversampling requires producing more output information than input information. It would be incredible for a NN to realize a system that could do this without requiring more memory and CPU cycles than a good oversampling algorithm, which can be derived analytically with various definitions of "optimal."

A 3rd or 4th order polynomial interpolator is pretty darn good and doesn't need a NN to find the coefficients.

Re: Neural networks emulate any guitar pedal for $120

#53

Post by duped »

ushakov wrote: post #32
duped wrote: post #19

The cool bit about this to me is that $120 in hardware is a the one-off prototyping cost. As a product it could be made much cheaper. Another benefit to a software defined pedal is that it can express sounds that cannot be replicated in analog. Emulation is boring. Train it to do stuff that I can't buy in a pedal!

but the coolest thing is that you can share and download models of one-of-a-kind amps or effect chains, which cannot be bought

Line6 was doing this 10-15 years ago and it wasn't that cool then. Eventide has some tools for it today tool, there's also the Owl, various teensy projects, and of course Kemper.

Re: Neural networks emulate any guitar pedal for $120

#55

Post by titzer »

montroser wrote: post #33
Applejinx wrote: post #23

…at MP3 quality. This is fine if you like that sort of thing. I would note that latency is very important here: it's not going to be nice to play through if it's incurring any significant latency.

Yes, latency is huge. Modern digital audio stacks in consumer OSes are still completely terrible at this. Not that it's an easy problem to solve. But it's pretty hard to beat elections flowing through an analog circuit, when in the digital side you have to: convert analog to digital, run through the kernel to get to user space, run the bits through the RNN, send back to kernel space, convert to analog and finally sen…

Yes, latency is really important, though it is important to note that digital signal processing doesn't need that huge stack. In fact, audio DSP chips have at least 25 years of history and the result is that today you can get things like the Vox AC30 which is a digital headphone amp--all digital--that has no perceptible latency. That one in particular, sounds pretty darn good, for just being a single battery-powered chip!

> In order to be competitive with a 1980s guitar pedal, you have to do all of that in under ~10ms latency, and that's just really hard still.

Well, don't use a whole PC with software stack. A custom embedded solution with DSP can easily manage.

> Even though we carry around these super computers in our pockets these days, there are still some things left where analog still beats the pants.

Again, it's not digital vs analog, it's massive software stack versus embedded hardware/software solution.

Re: Neural networks emulate any guitar pedal for $120

#56

Post by marcodiego »

shmageggy wrote: post #36
taneq wrote: post #20

Earlier quoted context omitted.

If you want to be pedantic it probably can't emulate a guitar pedal that you can tap a representation of a Turing machine into and it will only make a sound if the machine halts.

You can't create such a pedal in the first place, so...

You definitely can. You just cannot prove it will always make a sound.

Re: Neural networks emulate any guitar pedal for $120

#57

Post by ushakov »

kakwa_ wrote: post #51
montroser wrote: post #33

Earlier quoted context omitted.

Yes, latency is huge. Modern digital audio stacks in consumer OSes are still completely terrible at this. Not that it's an easy problem to solve. But it's pretty hard to beat elections flowing through an analog circuit, when in the digital side you have to: convert analog to digital, run through the kernel to get to user space, run the bits through the RNN, send back to kernel space, convert to analog and finally sen…

Also we had electronic simulators for various instruments for ages now. Things like Clavinova keyboards Piano or Line 6 Pods simulating Guitar/Bass amps & effects have been out their for decades now. And while they have been quite popular due to the sheer number of sonorities and the convenience they bring (possibility to play with an headset, extremely useful to play at night or in apartments), traditional analog se…

i totally agree

traditional methods were successful in emulating sounds, but they fail short at replicating the feel and response of the hardware they're trying to replicate

that's why you need neural networks!

Re: Neural networks emulate any guitar pedal for $120

#58

Post by titzer »

lunixbochs wrote: post #25
JD557 wrote: post #13

Earlier quoted context omitted.

They claim to be using a LSTM, and I believe that any RNN-like architecture should (in theory) be able to learn a loop pedal. If you aren't familiar with RNNs, think about it like a NN that instead of learning a input -> output function, learns a (input, state) -> (output, newState) function

Only if the entire loop audio fits into the RNN's hidden state? Or if you use some kind of external memory mechanism that gives the network access to previous audio.

This is the kind of thing where augmenting the NN with an actual raw audio buffer would allow it to mix in some of the signal from the past quite easily.

Re: Neural networks emulate any guitar pedal for $120

#59

Post by Applejinx »

hashkb wrote: post #46
montroser wrote: post #33

Earlier quoted context omitted.

Yes, latency is huge. Modern digital audio stacks in consumer OSes are still completely terrible at this. Not that it's an easy problem to solve. But it's pretty hard to beat elections flowing through an analog circuit, when in the digital side you have to: convert analog to digital, run through the kernel to get to user space, run the bits through the RNN, send back to kernel space, convert to analog and finally sen…

Also, the competition is not against vintage analog gear. Modern analog gear is having a true Renaissance, and this community can afford to support the Wampler's of the world. I don't understand the modelling camp at all, their stuff just doesn't sound good, nor is there any joy in working with it.

I feel the same but it's hell convincing the reductionists that they haven't got 'the thing, and the whole of the thing' in their little emulation.

There's also another element: if you have, say, a vintage Fender Champ and a Klon (or whatever) it's because you mean to project different expressions through your string handling and note-playing. At that level you've made a best effort to produce the most emotionally transparent and responsive signal chain, which you will then not think about once you've got it turned on and tweaked: ALL the settings are liable to sound 'good' and respond for you.

The modeling approach is so often "This is exactly that, but better, because here are twelve other Fender Champs and models of Klon to choose from!" and when the first claim isn't as true as we would like, and the second is a distraction and time-sink, that's not great.

I can tell when I've chosen wrongly in my music-making tools, because I flat-out stop making music. Even in a dilettantish way: it just stops being a thing. That's a concern.

Post reply on HN