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

81–90 of 160 posts

Re: Neural networks emulate any guitar pedal for $120

#81

Post by jcelerier »

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...

why couldn't you ? the code would just be

    extern char* turing_machine;
    int main() {
      process_turing_machine(turing_machine);
      beep();
    }

Re: Neural networks emulate any guitar pedal for $120

#82

Post by carlob »

I wonder how it deals with dynamic range. I've always been told that one shouldn't run an electric guitar directly through a stereo because the peaks might fry it. So I would expect that whatever comes out of the RPi doesn't have much dynamic range anyway so computer speakers would be ok, but sound would be kinda meh.

Am I missing something?

Re: Neural networks emulate any guitar pedal for $120

#83

Post by jeeceebees »

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.

LSTM stands for Long Short Term Memory. It's a recurrent network that learns what and how long things should be kept in its internal state buffer. It doesn't have a fixed state size because it's just learning a nonlinear function that takes an input and a state to an output and a new state. Obviously it can't model all possible, infinite length recurrences, but it can definitely do a pretty good job of approximating long term recurrence relations in complex signals.

Re: Neural networks emulate any guitar pedal for $120

#84

Post by PaulDavisThe1st »

smoldesu wrote: post #72
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.

In all fairness, it's running on a Raspberry Pi. There's plenty of ways you could improve latency and audio quality just by scaling the hardware to fit your needs. Plus, it's not like someone's going to flip their shit when they realize that one of the electric guitars was recorded at 44.1khz instead of 48/96/192khz

Improving CPU speed rarely has anything to do with audio processing latency unless you're close to overloading the CPU.

Re: Neural networks emulate any guitar pedal for $120

#86

Post by tpmx »

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.

MP3 @ 320 kbps is fine. Latency is a different thing. Also it seems like you're dismissing this without knowing anything about the actual latency (or sound quality).

Re: Neural networks emulate any guitar pedal for $120

#87

Post by PaulDavisThe1st »

hashkb wrote: post #42

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

"tone hounds"? There are many hundreds to many thousands of pedals. Everyone has their own favorites. There is no "right" in this world. There's just as much chance that whatever "error" a modelled pedal may embody is preferred by its users as there is that it will be deemed worse.

Re: Neural networks emulate any guitar pedal for $120

#88

Post by URSpider94 »

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.

There is no reason why this would run at “MP3 quality”, given that it would be a really bad idea to compress the audio data before running it through an algorithm. I would expect it’s at minimum CD quality, and perhaps better, depending on the fidelity of the A/D and D/A stages and the bandwidth of the algorithm.

Re: Neural networks emulate any guitar pedal for $120

#89

Post by PaulDavisThe1st »

ratww wrote: post #29
nonsapreiche wrote: post #15

Earlier quoted context omitted.

I wonder too, but I think the result will not be better than the samples from which you train it.

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.

Re: Neural networks emulate any guitar pedal for $120

#90

Post by URSpider94 »

duosonic wrote: post #85

Honest question: if you're a musician, what is the appeal of digital modeling? Is it purely affordability/accessibility, or are you drawn to it because it would create different sonic possibilities that you couldn't get from the original?

You mean, besides the appeal, what is the appeal? As an artist and a musician, you can have access to close approximations of sounds that would require a warehouse full of amps and dozens of pedals, costing tens of thousands of dollars - all in a Pi project box. That’s not just a little bit of affordability and convenience.
Post reply on HN