Deep Learning for Guitar Effect Emulation • Hacker News Board

Re: Deep Learning for Guitar Effect Emulation

#91

Post by zodiac » Mon, May 11, 2020, 3:48 PM UTC

swebs wrote: post #37

aea12 wrote: post #16

Earlier quoted context omitted.

Implementing a VST plugin is literally the exact definition of requiring strict latency guarantees. Your comment winds through a lot of unrelated comparisons to ultimately not make any sense. “Usually fast enough” are three words that guarantee failure in a live show/MIDI environment, which is a large use case of VST and its peers beyond production. By extension, “usually fast enough” further guarantees nobody will e…

No, the other guy is right. Technically the definition of real-time can have a lot of leeway. Here's the paper linked in the article. Note how the authors never define what they really mean by real-time. They even make statements like "runs 1.9 times faster than real-time". They certainly imply your definition, but there's plenty of wiggle room to say "Well technically, I wasn't lying" https://www.mdpi.com/2076-3417/…

In the context of e.g. offline video encoders "1.9x realtime" is a statement about throughput, not latency

Re: Deep Learning for Guitar Effect Emulation

#92

Post by wintermutestwin » Mon, May 11, 2020, 3:49 PM UTC

hashkb wrote: post #88

wintermutestwin wrote: post #66

"many purists argue that the sound of analog pedals can not be replaced by their digital counterparts." Truly effective modelling of analog pedals, tube amps and guitar cabs has been around for years and is way more cost effective from the bedroom to touring bands. The "purists" are hipsters who value the rarity of some pedals, massive pedalboards and their tube amps. I'm not knocking them - I understand why there is…

This is ad hominem. You haven't included any data. You are just as superstitious about your bedroom rig as I am about my basement rig.

I guess you are technically right, but this part of the discussion is highly subjective. I was merely pointing out that the quoted statement was subjective and I wasn't using "hipster" as a pejorative - I was actually being somewhat sympathetic to their view.

Overall, my goal was to add to this discussion by pointing out the massive progress that has been made and also to show off my supercool signal path in the hopes that it would be inspirational to fellow geeks like me.

Re: Deep Learning for Guitar Effect Emulation

#93

Post by munificent » Mon, May 11, 2020, 3:50 PM UTC

whiddershins wrote: post #39

fab1an wrote: post #3

Pretty cool, though I wonder what the latency of this would be if used as a plugin? The author says it works in real-time, but to non music/audio folks this could mean '100 ms latency is real-time enough, right?' Generally, I think the audio VST business is a really fun space to be in for a lifestyle business, as it is way too small to be attractive for VCs. It seems like a space that provides many niches for lots of…

Do solo or small shop vst plugin developers make any money? I’m curious if anyone has any direct knowledge about that. There are so many professional activities similar to that where no one makes any money and people really just do it for the love, and then there are seemingly similar things like that where people make surprisingly large amounts of money.

Steve Duda, the developer of Serum is kind of the poster child for this. He contracts out for pieces of the synth (UI design, resampler, filters), but he's mostly a one-man shop and, as I understand it, Serum pays the bills.

It's hard to tell how much Duda is an outlier, though, and how many other people could succesfully follow his path.

Re: Deep Learning for Guitar Effect Emulation

#94

Post by ben7799 » Mon, May 11, 2020, 3:52 PM UTC

willis936 wrote: post #49

A neat approach for sure. I am more interested in SPICE style modeled VSTs though. There's no need to throw ML at a simple math problem to get a bad approximation. I have not found many VSTs that seem like they're doing proper simulation of analog circuits. The VST space is filled with people claiming awesome results, but never revealing the sauce. If you're making a convincing sounding zener limiter, what are you ac…

Right..the Spice modeled version has a much better chance of catching the oddball behavior of guitar effects across the wide span of possible inputs.

Re: Deep Learning for Guitar Effect Emulation

#95

Post by munificent » Mon, May 11, 2020, 3:58 PM UTC

eru wrote: post #29

aea12 wrote: post #16

Earlier quoted context omitted.

Implementing a VST plugin is literally the exact definition of requiring strict latency guarantees. Your comment winds through a lot of unrelated comparisons to ultimately not make any sense. “Usually fast enough” are three words that guarantee failure in a live show/MIDI environment, which is a large use case of VST and its peers beyond production. By extension, “usually fast enough” further guarantees nobody will e…

The show won't collapse, if you have one glitch an hour.

If you drop an audio buffer and fire off a 22kHz impulse into a 50,000 watt soundsystem, you are going to have thousands of very unhappy people and likely some hearing damage.

Re: Deep Learning for Guitar Effect Emulation

#96

Post by mrob » Mon, May 11, 2020, 3:58 PM UTC

jelling wrote: post #8

> We find that the model is able to reproduce a sound nearly indistinguishable from the real analog pedal. Maybe for the average person or buried in the mix, but the audio samples were easy to distinguish for me as a guitarist. The NN samples unnatural decay were a dead give away.

I could also tell the difference, but I preferred the more staccato sound of the NN version.

Re: Deep Learning for Guitar Effect Emulation

#97

Post by mgamache » Mon, May 11, 2020, 4:01 PM UTC

It would be interesting to see how this responds to dynamics. For example, a favorite guitar sound is a fuzz cranked, but with the guitar volume turned down. This results in a compressed dirty sound that can overdrive into distortion if you hit the strings harder (attack).

Re: Deep Learning for Guitar Effect Emulation

#98

Post by munificent » Mon, May 11, 2020, 4:01 PM UTC

ratww wrote: post #10

ericfrederich wrote: post #6

So this seems similar to an IR (impulse response) where you get a snapshot of an amp mic'd up in a room with knobs fixed at a particular position. In the end, you don't get knobs to fiddle with. Awesome, I'd love to hear Josh from JHS Pedal's opinion on this.

This is even more impressive since regular IRs can't duplicate the distortion effect itself, only the frequency response

What is the difference between "distortion itself" and "only the frequency response"? Are you saying the phase response is important?

Re: Deep Learning for Guitar Effect Emulation

#99

Post by qppo » Mon, May 11, 2020, 4:08 PM UTC

fab1an wrote: post #3

Pretty cool, though I wonder what the latency of this would be if used as a plugin? The author says it works in real-time, but to non music/audio folks this could mean '100 ms latency is real-time enough, right?' Generally, I think the audio VST business is a really fun space to be in for a lifestyle business, as it is way too small to be attractive for VCs. It seems like a space that provides many niches for lots of…

I know of a few shops that took VC money. The big problem isn't the market size so much as how slow the market moves. The product lifetime of a plugin is around a decade. And users hate subscriptions. And it's really hard to determine the value you add to your customers. And no one wants to pay you.

It's basically a terrible place to be a developer in it for the money. Really fun work otherwise. The cool gigs are the ones where you build custom plugins for someone's crazy idea.

In consumer applications, plugins are used all the time for prototyping before you go to hardware. MATLAB is way too slow for anything useful.

Re: Deep Learning for Guitar Effect Emulation

#100

Post by jeffbee » Mon, May 11, 2020, 4:10 PM UTC

TheRealPomax wrote: post #78

alexlarsson wrote: post #30

Earlier quoted context omitted.

I assume by real-time he meant "able to produce samples at a rate equal to or higher than the audio output sample rate".

That's not what real time, means though. Real time processing means taking signals as they come in, and outputting the transformed result such that there is as close to no signal lag as possible. The output can in fact be wildly lower or higher resolution, real-time does not particularly say anything about that. It's all about whether the output plays (for practical purposes) at the perceived "same time" as the input…

Is that your private definition of "real-time"? I think it is common to define real-time processing by a specified, finite time between input and output. Many real-time processes are concerned more with the consistency of the latency than with its absolute value.