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

101–110 of 160 posts

Re: Neural networks emulate any guitar pedal for $120

#101

Post by riku_iki »

ushakov wrote: post #73
riku_iki wrote: post #69

Earlier quoted context omitted.

> this approach is not scalable (that's why the high cost) It may be opposite, most of the amps follow some classic schematic (e.g. jtm, plexi, princeton) with insignificant changes, so after building digital copies of some limited number of classical amps they can add new one rather fast. As result, fractal has about 100 high quality models already (average guitarist probably uses 5?). > the ML approach doesn't requ…

sure, but can it model my amp? i doubt they will ever add it! correct, ml requires data, but you don't need to capture every possible position to do a good prediction only a handful would suffice and let's be honest, how many presets do you really need (average guitarist probably uses 5?)

> sure, but can it model my amp? i doubt they will ever add it!

This is very different and more narrow use-case.

Also they have tone match like forever, you build signal chain close to your amp, then add tone match block, which applies ML to voice your digital signal chain close to recording.

Here is example: https://www.youtube.com/watch?v=hZnZ1nJODLo

Also in this example he didn't profile actual amp, but actual AC/DC recording, and result is very good I think.

> how many presets do you really need (average guitarist probably uses 5?)

But how you find this preset for your signal chain (guitar + speakers)? That's one of big points of frustration with kemper: one needs to go through hundreds profiles (not necessary good quality) to find one which will sound good with his signal chain.

With fractal: you take some basic preset, and change knobs to your tastes and goal as with real amp.

Re: Neural networks emulate any guitar pedal for $120

#102

Post by slver »

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…

A smartphone doesn't have super-low latency audio only because its makers have not set out to have it.

The only strength of analog processors is that they're dedicated. That an iPhone SoC and run dedicated audio-only OS on it, and there we go.

Re: Neural networks emulate any guitar pedal for $120

#104

Post by jtriangle »

ushakov wrote: post #28

have i mentioned yet that training only takes ~30 minutes and you only need ~3 minutes of data?

Could it work on a live amp like the Kemper or a quad cortex? And can the models be exported and shared?

Because if those two things were squared away, I could see this being an extremely viable project.

Re: Neural networks emulate any guitar pedal for $120

#105

Post by jtriangle »

hashkb wrote: post #42

Can any skeptics weigh in? To me, this kind of tech is centuries away from fooling tone hounds.

Andersons has a few YouTube videos where the Kemper profiler fools tone hounds enough that you can infer that it's already good enough. The NeuralDSP hardware is of at least similar quality, maybe better in some instances.

Sure if you run a null test these will fail, but in real life it's really up to how honest the tone hound in question is, and if you can trap them into being honest.

If you're talking product viability, something like the Pepsi challenge, double blind testing, would probably be effective marketing.

Re: Neural networks emulate any guitar pedal for $120

#106

Post by ratww »

PaulDavisThe1st wrote: post #89
ratww wrote: post #29

Earlier quoted context omitted.

Now that you mentioned samples: I wonder if neural networks will be able to help with polyphonic note detection, so we can trigger MIDI samples using an off-the-shelf guitar or other instruments. There have been a few recent advancements lately (Boss SY-1), but even the supposedly "ideal" solutions, that require a new polyphonic pickup, are not good at all. I have a Fishman Triple Play and a plugin whose name I forgo…

polyphonic note detection is largely solved at this point. But "solved" here means "when not doing the analysis in real time". The realtime solutions are not as good. NN's are not typically great at realtime either, so this may not help very much with this particular goal.

The video in TFA is in real time, so I don't believe your assumption is correct.

Re: Neural networks emulate any guitar pedal for $120

#107

Post by ushakov »

jtriangle wrote: post #104
ushakov wrote: post #28

have i mentioned yet that training only takes ~30 minutes and you only need ~3 minutes of data?

Could it work on a live amp like the Kemper or a quad cortex? And can the models be exported and shared? Because if those two things were squared away, I could see this being an extremely viable project.

yes! for training the model you’d need a separate computer/server though

Re: Neural networks emulate any guitar pedal for $120

#108

Post by ratww »

nwatson wrote: post #41
ratww wrote: post #29

Earlier quoted context omitted.

Now that you mentioned samples: I wonder if neural networks will be able to help with polyphonic note detection, so we can trigger MIDI samples using an off-the-shelf guitar or other instruments. There have been a few recent advancements lately (Boss SY-1), but even the supposedly "ideal" solutions, that require a new polyphonic pickup, are not good at all. I have a Fishman Triple Play and a plugin whose name I forgo…

In which Pat Metheny tries to replace his whole band with guitar-triggered control of real, non-guitar instruments (keyboards, drums, etc) ... "Orchestrion" ... https://youtu.be/KsYEOUKS4Yk

Yeah, it's honestly not that good. I think Metheny uses an Axon. Even with those you need to be very careful with your phrasing, you can't be too fast, you lose a lot of dynamic range and a lot of expressivity, sometimes notes just die, the latency is high...

Here's what Metheny said himself: "But the guitar‑to‑MIDI part has always been a problem. It's a question of physics. On input, I sort of have to rush. But I know how to rush. I play ahead."

It's fun for lots of things, and you can make lots of cool music, but it's still very limited to certain styles, dynamic ranges, phrasing, tempo, speeds...

Re: Neural networks emulate any guitar pedal for $120

#109

Post by ushakov »

hashkb wrote: post #42

Can any skeptics weigh in? To me, this kind of tech is centuries away from fooling tone hounds.

See "4.4. Listening Tests" of the research the technology is based on

https://acris.aalto.fi/ws/portalfiles/portal/41964332/Real_t...

those are MUSHRA tests, meaning only skilled listeners are allowed to participate https://en.wikipedia.org/wiki/MUSHRA

Re: Neural networks emulate any guitar pedal for $120

#110

Post by jcims »

keyth72 wrote: post #91
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.

...At mp3 quality As the creator of this project I can assure you that the audio used here is at least CD quality (44.1kHz 16bit). With the HiFiBerry hat the digital audio comes in at 24bit/192kHz. The NeuralPi DSP processes the audio at 44.1kHz with 32 bit floating point precision. No reason the sample rate can’t be higher though. Elk OS claims latency is less than 1ms, but I’d like to test and see exactly what the…

I wonder if it's possible to build a neural net that consists of layers of simulated passives and simple ICs.
Post reply on HN