Working Toward Computer-Augmented Music Traditions

Abstract

We discuss our work in modelling and generating music transcriptions using deep recurrent neural networks. In contrast to similar work, we focus on creating a rich evaluation methodology that seeks to address questions related to what a model has learned about the music, how useful it is for music practices, and its broader implications for music tradition. We engage with a specific homophonic music practice (session music), and present several examples of using our models for music composition in and out of the conventions of that idiom. We are currently exploring how these computer models can contribute to the tradition by engaging with its practitioners