Google is on the cutting edge of sound design.
Google Brain's Magenta division has unveiled its new project NSynth, a neural network of sounds that draws on the sonic makeup of roughly a thousand instruments.
“The blending of instruments is nothing new," critic Marc Weidenbaum told Wired. “Artistically, it could yield some cool stuff, and because it’s Google, people will follow their lead,” he says.
By analyzing the notes, the neural net—several layers of calculus run across a network of computer chips—learned the audible characteristics of each instrument. Then it created a mathematical “vector” for each one. Using these vectors, a machine can mimic the sound of each instrument—a Hammond organ or a clavichord, say—but it can also combine the sounds of the two.