Deep learning A.I. can imitate the distortion effects of iconic guitar gods

Music making is increasingly digitized here in 2020, but some analog audio effects are still very difficult to reproduce in this way. One of those effects is the kind of screeching guitar distortion favored by rock gods everywhere. Up to now, these effects, which involve guitar amplifiers, have been next to impossible to re-create digitally.

That’s now changed thanks to the work of researchers in the department of signal processing and acoustics at Finland’s Aalto University. Using deep learning artificial intelligence (A.I.), they have created a neural network for guitar distortion modeling that, for the first time, can fool blind-test listeners into thinking it’s the genuine article. Think of it like a Turing Test, cranked all the way up to a Spınal Tap-style 11.

“It has been the general belief of audio researchers for decades that the accurate imitation of the distorted sound of tube guitar amplifiers is very challenging,” Professor Vesa Välimäki told Digital Trends. “One reason is that the distortion is related to dynamic nonlinear behavior, which is known to be hard to simulate even theoretically. Another reason may be that distorted guitar sounds are usually quite prominent in music, so it appears difficult to hide any problems there; all inaccuracies will be very noticeable.”

Researchers recorded the guitar effects in a special anechoic chamber. Mikko Raskinen

To train the neural network to recreate a variety of distortion effects, all that is needed is a few minutes of audio recorded from the target amplifier. The researchers used “clean” audio recorded from an electric guitar in an anechoic chamber, and then ran it through an amplifier. This provided both an input in the form of the unblemished guitar sound, and an output in the form of the corresponding “target” guitar amplifier output.

“Training is done by feeding the neural network a short segment of clean guitar audio, and comparing the network’s output to the ‘target’ amplifier output,” Alec Wright, a doctoral student focused on audio processing using deep learning, told Digital Trends. “This comparison is done in the ‘loss function,’ which is simply an equation that represents how far the neural network output is from the target output, or, how ‘wrong’ the neural network model’s prediction was. The key is a process called ‘gradient descent,’ where you calculate how to adjust the neural network’s parameters very slightly, so that the neural network’s prediction is slightly closer to the target amplifier’s output. This process is then repeated thousands of times — or sometimes much more — until the neural network’s output stops improving.”

You can check out a demo of the A.I. in action here. A paper describing the work was recently published in the journal Applied Sciences.

Related posts

Latest posts

Google gives memory superpowers to Gemini for more natural chats

You will no longer have to look up past chats with Google’s chatbot. Thanks to the memory feature, it can now recall details from previous conversations.

Android 16’s latest beta promises deeper mobile photography controls

With Android 16 Beta 2, Google is upgrading the camera app framework with a hybrid exposure system, and granular controls for color temperature and tint levels.

Why are really old iPhones suddenly so popular?

In a trend driven by K-pop stars and celebrities in South Korea, old iPhone models and digital cameras have become a desirable accessory.

Apple is working on a mini-LED Studio Display, but the iMac Pro is nowhere to be found

Apple’s Studio Display could soon get a mini-LED upgrade to elevate it for professional users. Yet it’s also made me wonder if the iMac Pro is ever coming back.

Dell slashed the price of the Alienware m18 R2 gaming laptop with RTX 4080 by $420

The Alienware m18 R2 gaming laptop with the Nvidia GeForce RTX 4080 graphics card and 32GB of RAM is available from Dell for $2,380 following a $420 discount.

Possible iPhone 17 Air design looks strangely familiar

A fantastic concept video for the iPhone 17 Air has been released. It looks impressive yet somewhat familiar.

Like T-Mobile? You can pay your phone bill by playing games

T-Mobile customers can now work toward paying their monthly bill by playing mobile games in the Ad It Up app.

Galaxy S24 owners could fall a whole Android version behind the Pixel

If you own a Samsung device but not the new Galaxy S25, we have unfortunate news for you.

The competition between AMD and Nvidia is finally heating up

Nvidia has just announced the release date for its next GPU, and AMD is ready to compete.

Meta’s next big bet might be AI humanoid robots for at-home chores

Meta is reportedly moving forward with AI-powered humanoid robots. They will be developed by the same division that is behind its AI and wearable efforts.