ICLR 2019 Expo Talk
Machine Learning for Musical Creativity
Sponsor: Google AI
Abstract: Structure plays an essential role in the creative process of musicians, and artists in general. But finding good, and lasting, structures is hard, often taking many iterations over multiple centuries. In a sense, as a musical species, we have been sifting through centuries of “data” trying to extract the underlying patterns that represent the type of music that works best. Extracting patterns from very large datasets is something that machine learning (and deep learning in particular) excel at. At Google we are exploring different ways we can leverage deep learning to uncover some of the patterns in the music around us and provide tools for empowering musicians and amateurs alike. We will present some generative models for producing high-quality musical pieces and sounds, as well as discuss various ways that musicians have been using them creatively. We will finish with a demonstration of a tool we built to perform collaborative jazz improvization with a few of our models.