Live data from Hacker News

Show HN: SmartGuitarAmp – Guitar plugin made with deep learning

github.com

131–140 of 163 posts

Re: Show HN: SmartGuitarAmp – Guitar plugin made with deep learning

#131

Earlier quoted context omitted.

If most people (ie your audience) can't tell the difference, then why go with it?

Take it as a fact that you’ll commonly have higher standards than your audience. This applies to software, actors, musicians, whatever. That, and your experience affects your performance. It’s easier for an actor to act in a room full of props and other actors, versus a green screen. Easier for a musician to make music with the gear and tone that they prefer.

"...Take it as a fact that you’ll commonly have higher standards than your audience. This applies to software, actors, musicians, whatever..."

Can you explain this a bit more? I do not see this is commonly true, it is the exception and not the rule in many cases of 'someone and their audience'.

It might be true that that 'someone' believes it, however misguided.

Re: Show HN: SmartGuitarAmp – Guitar plugin made with deep learning

#132
post #125

I think that you can get lower latency and better sounding models with convolution. It's also quite fun to build your own impulse response library from things around your home, emulating the properties of your kitchen sink for example.

Convolution is linear, tube amps have many levels of nonlinear behavior.

Re: Show HN: SmartGuitarAmp – Guitar plugin made with deep learning

#133
post #61

Earlier quoted context omitted.

> The most popular guitar amps now are all solid state Maybe on the low end of the market, but tube amps still reign supreme for most serious players.

Many prominent artists are touring with modelling amps for years now. https://www.fractalaudio.com/artists/ There are many advantages. Less maintenance, lower stage volumes, better for in-ear-monitoring use, sound consistency, less weight to carry, and the ability to explore hundred of amps sounds with a single device eg. check https://wiki.fractalaudio.com/wiki/index.php?title=Amplifier...

Linking to an endorsement page doesn’t tell the whole story.

I would be pretty surprised if Metallica were using the technology you are describing. They have an extremely consistent setup that has worked for decades and an effectively infinite budget.

That’s just one concrete example.

I think a lot of the comments in this thread are missing the fact that if a player thinks a thing has irreproducable properties, they may be happier and more creative while using it.

Re: Show HN: SmartGuitarAmp – Guitar plugin made with deep learning

#134
post #114

Earlier quoted context omitted.

Milliwatts? Rubbish. Kids have been playing rock and roll through AC15s or 22W Deluxe Reverbs (or louder!) in garages and basements for decades. A 5W Champ or similar certainly can get loud but is fine for bedroom or apartment use, at least during daytime hours. As a teenager I played a Hot Rod Deluxe (40W!) in my parents' basement with no real complaints.

Crank your AC15 and play it in the basement, it will destroy your hearing pretty fast without protection. I used to take a homemade 5W amp outside and hear it echo in the woods. Fun times. Quick math—the Vox AC15 has speakers with around 100 dB SPL@1m,1W sensitivity, so if you’re cranked then it’s +24dB, and if you’re 2m away then that’s -12dB, and that’s 112 dB SPL, somewhere around “car horn” or “chainsaw” on the l…

I’d really like a citation on the medical literature portion of your comment.

I am under the impression I am well read on this topic, and I don’t recognize that claim.

Re: Show HN: SmartGuitarAmp – Guitar plugin made with deep learning

#135
post #44

For people who don’t play guitar, this is really commonplace technology now. Engineers worked out how to model the circuit behavior of any amp a while ago. Powerful valve guitar amps have really interesting effects on the waveform particularly when driven hard, but that valve technology is expensive, unreliable, bulky, and very loud when producing some of the most sought after tones. The most popular guitar amps now…

The idea that this technology is "the most popular" is incorrect as is the idea that tube amps are unreliable.

The katana and fender GT sound "fine" but the assertion that they can model traditional tube amps well enough for stage use is also a little suspect. Those specific amps sound thin and lifeless compared to the amps they attempt to model.

Where these types of amps shine is that they're lighter and you can have a more consistent sound at lower volumes. For a person in their house who isn't really worried about having a specific sound or may not even know the difference between british and american voiced amps these are great options. Also the volume issue only comes into play when we're thinking about gain and compression. My fender Deluxe Reverb sounds amazing at low volume.

The AxeFx and helix stuff is a little better but that stuff is way more expensive than your average tube amp, particularly on the used market. Your average 40 watt tube amp from fender, vox, marshall, etc will run you $700-$1500 while these high end modellers can easily be $2500+.

As far as tube amps being unreliable goes I'd love to see some sources on that. I've played fender amps from the 50s and marshalls from the 60s that sound every bit as good today as they did when they were made.

I work in very high end music retail where I'm fortunate enough to get to play all kinds of new and very old gear. I can confidently say that modelling is getting better and has drastically improved in the last 20 years but still has a ways to go if it's going to completely replace tube amps for stage and studio use.

Re: Show HN: SmartGuitarAmp – Guitar plugin made with deep learning

#136

Earlier quoted context omitted.

Yeah I didn’t get this statement. I only play tube amps, and most guitarists I know only play tube amps. I actually don’t know anyone that plays a modeling amp. Maybe they’re more popular outside of my sphere, but even with popular YouTube guitars players, they all play tube amps. Mostly Fender.

I never saw the point of getting a real tube amp unless you play exclusively in a studio or rehearsal room. The volume required to crank and get the best of it sounds it makes it too loud for almost any residential area. One of the best features of modeling amps is that you can get the sound of a cranked amp set at a high volume, with low/moderate real volume or even with head-phones. Even in a rehearsal room, real a…

This is really only an issue if you're driving 100 watt amps to the brink to get higher gain. You can buy 20 and even 10 watt tube amps that sound fantastic and are much more manageable.

Guitar players always think you need a gigantic marshall stack to get good tone when for most people that is way too much and they'll never hear it the way it's supposed to sound.

Re: Show HN: SmartGuitarAmp – Guitar plugin made with deep learning

#137
post #114

Earlier quoted context omitted.

Milliwatts? Rubbish. Kids have been playing rock and roll through AC15s or 22W Deluxe Reverbs (or louder!) in garages and basements for decades. A 5W Champ or similar certainly can get loud but is fine for bedroom or apartment use, at least during daytime hours. As a teenager I played a Hot Rod Deluxe (40W!) in my parents' basement with no real complaints.

Crank your AC15 and play it in the basement, it will destroy your hearing pretty fast without protection. I used to take a homemade 5W amp outside and hear it echo in the woods. Fun times. Quick math—the Vox AC15 has speakers with around 100 dB SPL@1m,1W sensitivity, so if you’re cranked then it’s +24dB, and if you’re 2m away then that’s -12dB, and that’s 112 dB SPL, somewhere around “car horn” or “chainsaw” on the l…

Why would you need to crank it at all? That amp is gonna sound fantastic at half volume. For grit they make excellent overdrives these days.

Re: Show HN: SmartGuitarAmp – Guitar plugin made with deep learning

#138
Wow, I am blown away by the feedback and discussion from everyone here. Just want to say that this is an extremely different experience from any other site I’ve been on, so thank you for that. Future goals for this project are to improve the audio quality and get community contributions for model training of different hardware. It’s very much still an experimental project, but I wanted to give an idea of what is possible using deep learning for audio applications.

Re: Show HN: SmartGuitarAmp – Guitar plugin made with deep learning

#139
post #81

Hey, saw your comments a couple of weeks ago on the wavenetVA repo, this is looking great! Will try training spring reverb and analog tape, those have been pretty hard to model with DSP. Also, what do you think about diffwave? Only seen speech examples so far but seems an order of magnitude faster than wavenet. https://github.com/lmnt-com/diffwave

Nice, I’ll have to look into diffwave, have not heard of that. You may have difficulty training on reverb effects due to the nature of the WaveNet model. It works well for distortion, but for effects that extend past around 50 milliseconds like reverb or delay, it might not be able to capture it properly.

Re: Show HN: SmartGuitarAmp – Guitar plugin made with deep learning

#140

Earlier quoted context omitted.

It looks pretty neat, awesome form factor. It’d be cool to know more details without having to sign up though.

Gonna fire off a kickstarter here in about a week and wanted to collect some followers as far ahead as possible! Promo is definitely not my jam! You're right, that page is totally worthless. Anyway, it's super simple. I just wanted a type-c version of what was already out there, and maybe for it to sound 'reasonable' at a sub $30 price point. It is only 16-bit 48kHz, but does a great job at dialing in tone, recording…

Thanks for the info, sounds like a great product.
Post reply on HN