It’s only a matter of time until Bassnectar gets his hands on his own AI instruments.
Google Magenta—a small team of AI researchers inside the internet giant building computer systems that can make their own art— is now in the process of harnessing artificial intelligence in order to create never-before-heard instruments, Wired reports. The project is called N-Synth.
“Unlike a traditional synthesizer which generates audio from hand-designed components like oscillators and wavetables, NSynth uses deep neural networks to generate sounds at the level of individual samples,” the team details in a blog post.
The program utilizes real instruments such as the Glockenspiel, Bass, or Organ, which N-Synth then analyzes in order to form new sounds using the numerical characteristics from the original instrument.
“NSynth begins with a massive database of sounds. Engel and team collected a wide range of notes from about a thousand different instruments and then fed them into a neural network. 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,” Wired reports.
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.
The Google Magenta team will showcase the technology this week at Moogfest, the annual music, art, and technology festival. The annual celebration continues to push the boundaries of music and technology.