DeepJ: Style-Specific Music Generation
This work addresses the need for more practical music generation tools for artists, filmmakers, and composers, though it appears incremental as it builds on existing deep learning methods.
The paper tackles the problem of generating music with user-tunable parameters by introducing DeepJ, an end-to-end generative model that composes music conditioned on composer styles, and it shows improvement over the Biaxial LSTM approach in human evaluations.
Recent advances in deep neural networks have enabled algorithms to compose music that is comparable to music composed by humans. However, few algorithms allow the user to generate music with tunable parameters. The ability to tune properties of generated music will yield more practical benefits for aiding artists, filmmakers, and composers in their creative tasks. In this paper, we introduce DeepJ - an end-to-end generative model that is capable of composing music conditioned on a specific mixture of composer styles. Our innovations include methods to learn musical style and music dynamics. We use our model to demonstrate a simple technique for controlling the style of generated music as a proof of concept. Evaluation of our model using human raters shows that we have improved over the Biaxial LSTM approach.