Adaptable Symbolic Music Infilling with MIDI-RWKV
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914279024754688 |
|---|---|
| author | Zhou-Zheng, Christian Pasquier, Philippe |
| author_facet | Zhou-Zheng, Christian Pasquier, Philippe |
| contents | Existing work in automatic music generation has mostly focused on end-to-end systems that generate either entire compositions or continuations of pieces, which are difficult for composers to iterate on. The area of computer-assisted composition, where generative models integrate into existing creative workflows, remains comparatively underexplored. In this study, we address the tasks of model style adaptation and multi-track, long-context, and controllable symbolic music infilling to enhance the process of computer-assisted composition. We present MIDI-RWKV, a small foundation 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 style adaptation in the very-low-sample regime. We evaluate MIDI-RWKV and its state tuning on several quantitative and qualitative metrics with respect to existing models, and release model weights and code at https://github.com/christianazinn/MIDI-RWKV. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_13001 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Adaptable Symbolic Music Infilling with MIDI-RWKV Zhou-Zheng, Christian Pasquier, Philippe Sound Machine Learning Multimedia Audio and Speech Processing I.2.1; I.2.6; H.5.5; J.5 Existing work in automatic music generation has mostly focused on end-to-end systems that generate either entire compositions or continuations of pieces, which are difficult for composers to iterate on. The area of computer-assisted composition, where generative models integrate into existing creative workflows, remains comparatively underexplored. In this study, we address the tasks of model style adaptation and multi-track, long-context, and controllable symbolic music infilling to enhance the process of computer-assisted composition. We present MIDI-RWKV, a small foundation 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 style adaptation in the very-low-sample regime. We evaluate MIDI-RWKV and its state tuning on several quantitative and qualitative metrics with respect to existing models, and release model weights and code at https://github.com/christianazinn/MIDI-RWKV. |
| title | Adaptable Symbolic Music Infilling with MIDI-RWKV |
| topic | Sound Machine Learning Multimedia Audio and Speech Processing I.2.1; I.2.6; H.5.5; J.5 |
| url | https://arxiv.org/abs/2506.13001 |