Bach2Bach: Generating Music Using A Deep Reinforcement Learning Approach
This addresses music generation for AI applications, but it appears incremental as it builds on existing deep learning and reinforcement learning techniques without claiming broad SOTA.
The paper tackled the problem of generating polyphonic music by developing a deep reinforcement learning architecture that incorporates a Bi-axial LSTM and DQN to ensure coherence with musical rules, resulting in good quantitative and qualitative performance in composition.
A model of music needs to have the ability to recall past details and have a clear, coherent understanding of musical structure. Detailed in the paper is a deep reinforcement learning architecture that predicts and generates polyphonic music aligned with musical rules. The probabilistic model presented is a Bi-axial LSTM trained with a pseudo-kernel reminiscent of a convolutional kernel. To encourage exploration and impose greater global coherence on the generated music, a deep reinforcement learning approach DQN is adopted. When analyzed quantitatively and qualitatively, this approach performs well in composing polyphonic music.