Lead Sheet Generation and Arrangement by Conditional Generative Adversarial Network
This addresses a domain-specific problem for music generation, offering an incremental approach to overcome limitations in existing notations.
The paper tackles the challenge of generating multi-instrument music across arbitrary genres by proposing a new task called lead sheet arrangement, using a recurrent convolutional generative model with new harmonic features to generate eight-bar lead sheets and arrangements.
Research on automatic music generation has seen great progress due to the development of deep neural networks. However, the generation of multi-instrument music of arbitrary genres still remains a challenge. Existing research either works on lead sheets or multi-track piano-rolls found in MIDIs, but both musical notations have their limits. In this work, we propose a new task called lead sheet arrangement to avoid such limits. A new recurrent convolutional generative model for the task is proposed, along with three new symbolic-domain harmonic features to facilitate learning from unpaired lead sheets and MIDIs. Our model can generate lead sheets and their arrangements of eight-bar long. Audio samples of the generated result can be found at https://drive.google.com/open?id=1c0FfODTpudmLvuKBbc23VBCgQizY6-Rk