Google's AI Invents Sounds Humans Have Never Heard Before

Engel and Resnick are part of Google Magenta--a small team of AI researchers inside the internet giant building computer systems that can make their own art--and this is their latest project. Neural networks are complex mathematical systems that can learn tasks by analyzing large amounts of data, and in recent years they've proven to be an enormously effective way of recognizing objects and faces in photos, identifying commands spoken into smartphones, and translating from one language to another, among other tasks. 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. In addition to the NSynth "slider" that Engel recently demonstrated at Google headquarters, the team has also built a two-dimensional interface that lets you explore the audible space between four different instruments at once.