Live data from Hacker News

Neural networks emulate any guitar pedal for $120

hackaday.com

31–40 of 160 posts

Re: Neural networks emulate any guitar pedal for $120

#31
post #11

Earlier quoted context omitted.

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.

you can download models online, no need to train yourself, which i agree is time consuming

There's even some potential for a small market of those. Lots of guitar players I know but Kemper models, or convolution impulses.

Re: Neural networks emulate any guitar pedal for $120

#32
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

Re: Neural networks emulate any guitar pedal for $120

#33

…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 send to an output.

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.

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.

Re: Neural networks emulate any guitar pedal for $120

#35
post #32
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

That's the business model of Kemper (https://www.kemper-amps.com/)

Re: Neural networks emulate any guitar pedal for $120

#36
post #20
post #7

any 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.

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...

Re: Neural networks emulate any guitar pedal for $120

#37

…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.

Just switch the Pi for a FPGA and the problem should be fixed.

Re: Neural networks emulate any guitar pedal for $120

#38
post #14

As much as I'm torn with my feelings about nVidia as a company, especially recently with their attempts to artificially limit hardware you own, I must admit Jetson family is incredibly capable and very well executed. I've been using Jetsons as RasPi replacements wherever I can, they are not only more capable but also much more reliable than RPI4s, in my not so limited experience.

Extremely expensive. Or overpriced?

I wouldn't say that. 2GB dev kit is $50 depending on where you buy them. That's much more bang for the buck, even if you opt out using the tensor cores they were designed for.

Re: Neural networks emulate any guitar pedal for $120

#39
post #32

Earlier quoted context omitted.

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

That's the business model of Kemper ( https://www.kemper-amps.com/ )

yes, except you don't need to purchase a $1000+ device

this thing runs on consumer-grade hardware

Re: Neural networks emulate any guitar pedal for $120

#40
I recently watched a video[1] by Rhett Shull where he compared Neural Capture of a Quad Cortex[2] to real pedals.

I'm not a musician, but even I could easily tell the difference a lot of the time. It didn't sound bad, but there were clearly aspects the Neural Capture failed to, well, capture.

Still, early days.

[1]: https://www.youtube.com/watch?v=4SSOJxZHolc

[2]: https://neuraldsp.com/quad-cortex

Post reply on HN