Personalizable Long-Context Symbolic Music Infilling with MIDI-RWKV
This work addresses the need for iterative human-machine collaboration in music composition, offering a domain-specific solution for musicians and creators.
The paper tackles the problem of enabling interactive computer-assisted music composition by introducing a personalizable, multi-track, long-context symbolic music infilling model, achieving efficient and coherent musical cocreation on edge devices with effective personalization in low-sample regimes.
Existing work in automatic music generation has primarily focused on end-to-end systems that produce complete compositions or continuations. However, because musical composition is typically an iterative process, such systems make it difficult to engage in the back-and-forth between human and machine that is essential to computer-assisted creativity. In this study, we address the task of personalizable, multi-track, long-context, and controllable symbolic music infilling to enhance the process of computer-assisted composition. We present MIDI-RWKV, a novel model based on the RWKV-7 linear architecture, to enable efficient and coherent musical cocreation on edge devices. We also demonstrate that MIDI-RWKV admits an effective method of finetuning its initial state for personalization in the very-low-sample regime. We evaluate MIDI-RWKV and its state tuning on several quantitative and qualitative metrics, and release model weights and code at https://github.com/christianazinn/MIDI-RWKV.