Google's New AI Can Make Sounds We've Never Heard Before
Notes from approximately a thousand instruments.
Google‘s newest project is called NSynth, a program that can provide musicians with an entirely new set of tools to create music. It uses a huge database of sounds, and the NSynth team then collects notes from approximately a thousand instruments and then feeds them into a neural network. The neural net is able to run algorithms to learn about these notes, and then create a mathematical vector for each one. By doing so, it results in a machine that can mimic the sound of each instrument that can also combine these sounds.
By using technology, traditional instruments and its corresponding sounds can now be manipulated and fused, which will allow musicians a much wider range of notes to experiment with. Tools already include sliders that can merge sounds together, to two-dimensional interfaces that allows one to explore the audible space between four different instruments at once. Learn more about the project on its site here.
