Generative AI Now Encroaching On Music

While it might not seem like it to a novice, music turns out to be a highly mathematical endeavor with precise ratios between chords and notes as well as overall structure of rhythm and timing. This is especially true of popular music which has even more recognizable repeating patterns and trends, making it unfortunately an easy target for modern generative AI which is capable of analyzing huge amounts of data and creating arguably unique creations. This one, called Suno, does just that for better or worse.

Unlike other generative AI offerings that are currently available for creating music, this one is not only capable of generating the musical underpinnings of the song itself but can additionally create a layer of intelligible vocals as well. A deeper investigation of the technology by Rolling Stone found that the tool uses its own models to come up with the music and then offloads the text generation for the vocals to ChatGPT, finally using the generated lyrics to generate fairly convincing vocals. Like image and text generation models that have come out in the last few years, this has the potential to be significantly disruptive.

While we’re not particularly excited about living in a world where humans toil while the machines create art and not the other way around, at best we could hope for a world where real musicians use these models as tools to enhance their creativity rather than being outright substitutes, much like ChatGPT itself currently is for programmers. That might be an overly optimistic view, though, and only time will tell.

MotorMouth

MotorMouth For Future Artificial Humans

When our new computer overlord arrives it’ll likely give orders using an electromagnetic speaker (or more likely, by texting instead of talking). But for a merely artificial human being, shouldn’t we use an artificial mouth with vocal cords chords, nasal cavity, tongue,  teeth and lips? Work on such a thing is scarce these days, but [Martin Riches] developed a delightful one called MotorMouth between 1996 and 1999.

It’s delightful for its use of a Z80 processor and assembly language, things many of us remember fondly, as well as its transparent side panel, allowing us to see the workings in action. As you’ll see and hear in the video below, it works quite well given the extreme difficulty of the task.

Continue reading “MotorMouth For Future Artificial Humans”

Automating Rock Band Vocals

rockband_audio_simulator

When it comes to Rock Band, our friends suck at singing. No, really.

We’re cool with them beating on the drum set completely off-time, but the sound of them trying to sing “Tom Sawyer” makes us want to cut out our eardrums.

We’re willing to bet that Cornell students [Gautam Kamath and Dominick Grochowina] have friends like ours. Their Electrical and Computer Engineering final project aims to remove the tone deaf from in front of the microphone, allowing a computer to sing vocals instead.

Since Rock Band simply listens for the proper frequency to be sung, the pair figured it would be easy enough to monitor the game’s output and feed computer-generated signals back into the microphone. Once the game’s vocal bar is isolated via a series of filters, an ATMega644 is used to interpret the notes and generate the corresponding tone via a speaker.

While automating Rock Band gameplay is nothing new, we don’t recall seeing anyone try to cut the singer from the band. We think it’s a pretty cool concept – rock on!

Edit: Updated with video

Continue reading “Automating Rock Band Vocals”