Re-Creating Pink Floyd In The Name Of Speech

September 1, 2023 by Kristina Panos 18 Comments

For people who have lost the ability to speak, the future may include brain implants that bring that ability back. But could these brain implants also allow them to sing? Researchers believe that, all in all, it’s just another brick in the wall.

In a new study published in PLOS Biology, twenty-nine people who were already being monitored for epileptic seizures participated via a postage stamp-sized array of electrodes implanted directly on the surface of their brains. As the participants were exposed to Pink Floyd’s Another Brick In the Wall, Part 1, the researchers gathered data from several areas of the brain, each attuned to a different musical element such as harmony, rhythm, and so on. Then the researchers used machine learning to reconstruct the audio heard by the participants using their brainwaves.

First, an AI model looked at the data generated from the brains’ responses to components of the song, like the changes in rhythm, pitch, and tone. Then a second model rejiggered the piecemeal song and estimated the sounds heard by the patients. Of the seven audio samples published in the study results, we think #3 sounds the most like the song. It’s kind of creepy but ultimately very cool. What do you think?

Continue reading “Re-Creating Pink Floyd In The Name Of Speech” →

Guitar Distortion With Diodes In Code, Not Hardware

August 23, 2023 by Dan Maloney 14 Comments

Guitarists will do just about anything to get just the right sound out of their setup, including purposely introducing all manner of distortion into the signal. It seems counter-intuitive, but it works, at least when it’s done right. But what exactly is going on with the signal? And is there a way to simulate it? Of course there is, and all it takes is a little math and some Arduino code.

Now, there are a lot of different techniques for modifying the signal from an electric guitar, but perhaps the simplest is the humble diode clipping circuit. It just uses an op-amp with antiparallel diodes either in series in the feedback loop or shunting the output to ground. The diodes clip the tops and bottoms off of the sine waves, turning them into something closer to a square wave, adding those extra harmonics that really fatten the sound. It’s a simple hack that’s easy to implement in hardware, enough so that distortion pedals galore are commercially available.

In the video below, [Sebastian] explains that this distortion is also pretty easy to reproduce algorithmically. He breaks down the math behind this, which is actually pretty approachable — a step function with a linear part, a quadratic section, and a hard-clipping function. He also derives a second, natural exponent step function from the Schockley diode equation that is less computationally demanding. To implement these models, [Sebastian] chose an Arduino GIGA R1 WiFi, using an ADC to digitize the guitar signal and devoting a DAC to each of the two algorithms. Each distortion effect has its own charms; we prefer the harsher step function over the exponential algorithm, but different strokes.

Kudos to [Sebastian] for this easy-to-understand treatment of what could otherwise be a difficult subject to digest. We didn’t really expect that a guitar distortion pedal would lead down the rabbit hole to diode theory and digital signal processing, but we’re glad it did.

Continue reading “Guitar Distortion With Diodes In Code, Not Hardware” →

An Effects Pedal For Keyboards (and Mice)

August 21, 2023 by Bryan Cockfield 4 Comments

Effects pedals for musical instruments like electric guitars can really expand a musician’s range with the instrument. Adding things like distortion, echo, and reverb at the push of a button can really transform the sound of a guitar and add depth to a performance. But [Guy] wondered why these effects should be limited to analog signals such as those from musical instruments, and set about to apply a number of effects to the use of computer keyboards and mice with this HID effects pedal.

The mouse is perhaps the closer of the two to an analog device, so the translations from the effects pedal are somewhat intuitive. Reverb causes movements in the mouse to take a little bit of extra time before coming to a stop, which gives it the effect of “coasting”. Distortion can add randomness to the overall mouse movements, but it can also be turned down and even reversed, acting instead as a noise filter and smoothing out mouse movements. There’s also a looper, which can replay mouse movements indefinitely and a crossover, which allows the mouse to act as a keyboard.

For the keyboard, included effects are a tremolo, which modulates between upper- and lower-case at certain intervals; echo, which repeats keypresses; and a pitch-shift which outputs a “higher” character in the alphabet above whichever one has been pressed. Like the mouse, there’s also a crossover mode which allows the keyboard to be used as a mouse.

The device looks and feels like an effects pedal for a guitar would, with a RP2040 inside to intercept HID information, do the signal processing, and then output the result to the computer. And, while [Guy] admits this was a fun project with not many practical uses, there are a couple handy ones including potentially the distortion effect to smooth out mouse inputs for those with neuromuscular disorders or the mouse looper to act as a mouse jiggler for those with micromanaging employers. It’s also reprogrammable, and as we’ve seen since time immemorial having a programmable foot keyboard can be extremely handy for certain workflows.

Continue reading “An Effects Pedal For Keyboards (and Mice)” →

Modeling A Guitar For Circuit Simulation

August 19, 2023 by Bryan Cockfield 20 Comments

Guitar effects have come a long way from the jangly, unaltered sounds of the 1950s when rock and roll started picking up steam. Starting in large part with [Jimi Hendrix] in the 60s, the number of available effects available to guitarists snowballed in the following decades step-by-step with the burgeoning electronics industry. Now, there are tons of effects, from simple analog devices that would have been familiar to [Hendrix] to complex, far-reaching, digital effects available to anyone with a computer. Another thing available to modern guitarists is the ability to model these effects and guitars in circuit simulators, as [Iain] does.

[Ian] plays a Fender Stratocaster, but in order to build effects pedals and amplifiers for it with the exact desired sound, he needed a way to model its equivalent circuit. For a simple DC circuit, this isn’t too difficult since it just requires measuring the resistance, capacitance, and inductance of the overall circuit and can be done with something as simple as a multimeter. But for something with the wide frequency range of a guitar, a little bit more effort needs to go into creating an accurate model. [Iain] is using an Analog Discovery as a vector network analyzer to get all of the raw data he needs for the model before moving on to some in-depth calculations.

[Iain] takes us through all of the methods of figuring out the equivalent impedance of his guitar and its cabling using simple methods capable of being done largely by hand and more advanced techniques like finding numerical solutions. By analyzing the impedance of the pickup, tone and volume controls, and cable, this deep dive into the complexities of building an accurate equivalent circuit model for his guitar could be replicated by anyone else looking to build effects for their specific guitars. If you’re looking for a more digital solution, though, we’ve seen some impressive effects built using other tools unavailable to guitarists in days of yore, such as MIDI and the Raspberry Pi.

A Turing-Complete CPU In Sunvox? Why Not!

August 17, 2023 by Dave Rowntree 7 Comments

Day-time software engineer and part-time musician, [Logickin,] knows a thing or two about programming the SunVox modular synthesiser and tracker software. Whilst the software is normally used for creating music and sound effects, they decided to really push it, and create the VOXCOM-1610, a functional turing-complete CPU inside SunVox, just for fun.

For those who haven’t come across SunVox before now, this software is a highly programmable visual environment for building up custom synthesisers, piecing signals together to create rhythms — that’s the ‘tracker’ bit — as well as interfacing to input devices such as MIDI and many others. It does look like a lot of fun, but just like CPUs created in Minecraft, just because, this seems to be the first time someone has built one inside this particular music app. The VOXCOM 1610 is a fully functional 10 Hz, 16-bit computer. It boasts 2KB of ROM, 256 bytes of RAM (expandable to 128 KB), and 8 general registers for data exchange between components. If you don’t fancy manually poking bits into the ROM to enter your software, then you’re in luck as [Logickin] has provided an assembler (in Java) that should ease the process a lot. The ABI will look very familiar to anyone who’s ever touched assembler before, although as you’d expect, it is quite light on addressing modes.

Now, all that is needed is for someone to port Doom to this and we’ll have it all. We think that is unlikely to happen. For those who pay attention, we did see one neat SunVox project in the past, which is certainly eye-catching as well as eardrum-bursting.

Thanks to [elbien] for the tip!

GETMusic Uses Machine Learning To Generate Music, Understands Tracks

July 27, 2023 by Donald Papp 10 Comments

Music generation guided by machine learning can make great projects, but there’s not usually much apparent control over the results. The system makes what it makes, and it’s an achievement if the results are not obvious cacophony. But that’s all different with GETMusic which allows for a much more involved approach because it understands and is able to create music by tracks. Among other things, this means one can generate a basic rhythm and melody first, then add additional elements to those existing ones, leaving the previous elements unchanged.

GETMusic can make music from scratch, or guided from examples, and under the hood uses a diffusion-based approach similar to the method behind AI image generators like Stable Diffusion. We’ve previously covered how Stable Diffusion works, but instead of images the same basic principles are used to guide the model from random noise to useful tracks of music.

Just a few years ago we saw a neural network trained to generate Bach, and while it was capable of moments of brilliance, it didn’t produce uniformly-listenable output. GETMusic is on an entirely different level. The model and code are available online and there is a research paper to accompany it.

You can watch a video putting it through its paces just below the page break, and there are more videos on the project summary page.

Continue reading “GETMusic Uses Machine Learning To Generate Music, Understands Tracks” →

RoboPianist Is A Simulation For Advancing Robotic Control

July 21, 2023 by Lewin Day 10 Comments

Researchers at Google have posed themselves an interesting problem to solve: mastering the piano. However, they’re not trying to teach themselves, but a pair of simulated anthropomorphic robotic hands instead. Enter RoboPianist.

The hope is that the RoboPianist platform can help benchmark “high-dimensional control, targeted at testing high spatial and temporal precision, coordination, and planning, all with an underactuated system frequently making-and-breaking contacts.”

If that all sounds like a bit much to follow, the basic gist is that playing the piano takes a ton of coordination and control. Doing it in a musical way requires both high speed and perfect timing, further upping the challenge. The team hopes that by developing control strategies that can master the piano, they will more broadly learn about techniques useful for two-handed, multi-fingered control. To that end, RoboPianist models a pair of robot hands with 22 actuators each, or 44 in total. Much like human hands, the robot hands are underactuated by design, meaning they have less actuators than their total degrees of freedom.

Continue reading “RoboPianist Is A Simulation For Advancing Robotic Control” →