rsp1-LookingOutwards

NSynth: Neural Audio Synthesis

NSynth is Google Magenta’s—a small team of Google AI researchers —latest project. Their main pitch was that this new system will provide musicians with an entirely new range of tools for making music. It take different sounds from different instruments, and blends them together creating an entirely new sound as the creator can also alter how much of one sound is used.

According to an article in the New York Times, “The project is part of a growing effort to generate art through a set of A.I. techniques that have only recently come of age. Called deep neural networks, these complex mathematical systems allow machines to learn specific behavior by analyzing vast amounts of data. ” (https://www.nytimes.com/2017/08/14/arts/design/google-how-ai-creates-new-music-and-new-artists-project-magenta.html)

 

The following link below contains samples of the types of sounds that NSynth can generate:

https://magenta.tensorflow.org/nsynth

Below is an interactive page where you can mix and match your own sounds:

https://experiments.withgoogle.com/ai/sound-maker/view/