Learning the Long-Term Structure of the Blues

In general music composed by recurrent neural networks (RNNs) suffers from a lack of global structure. Though networks can learn note-by-note transition probabilities and even reproduce phrases, they have been unable to learn an entire musical form and use that knowledge to guide composition. In this study, we describe model details and present experimental results showing that LSTM successfully learns a form of blues music and is able to compose novel (and some listeners believe pleasing) melodies in that style. Remarkably, once the network has found the relevant structure it does not drift from it: LSTM is able to play the blues with good timing and proper structure as long as one is willing to listen. A note to referees: As the output of the network is musical, it is difficult to gain an appreciation by just reading the paper. The text references a URL containing helpful musical examples (www.idsia.ch/ ̃doug/blues/index.html). If this paper is accepted at ICANN, the authors look forward to playing some of these passages as part of the presentation. This note will be deleted before publication! The paper is 6 pages long without this note.