Google Creates Neural Network Synthesizer Called NSynth

Google, through one of its many research companies; this one called Magenta, has developed a synthesizer called "NSynth". A synthesizer algorithm that uses Neural Networks to essentially study what makes up a particular sound at its very core, and then synthesizes a whole new sound by using these specific characteristics. The sound could then be played through an X/Y pad, or potentially even a keyboard controller. As part of its ongoing research in what kind of interface would work best however, the particular set up Google has come up with, resembles basically a Korg Kaoss Pad, and is called the NSynth Super; a hardware controller created in collaboration with Creative Lab, of which its instructions can be obtained on Google's Github, and is fully open-source. More info here.

Typical finished product of a DIY NSynth Super © Google

As for Magenta, a little background on the company is that its role is to essentially find out how Machine Learning; the way in which Artificial Intelligence is being achieved, can help artists be more creative. As stated on the Magenta website, their method: "Involves developing new deep learning and reinforcement learning algorithms for generating songs, images, drawings, and other materials. But it's also an exploration in building smart tools and interfaces that allow artists and musicians to extend (not replace!) their processes using these models. Magenta was started by some researchers and engineers from the Google Brain team but many others have contributed significantly to the project. We use TensorFlow and release our models and tools in open source on our GitHub."

So go on, give it a try! Check out the Creative Lab/Google Github and start building one yourself. Also, please take some time to watch the video below.

#Electro #Google #Magenta #CreativeLab #NSynth #NeuralNetworks