Music Proofreading with RefinPaint: Where and How to Modify Compositions given Context
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913574924845056 |
|---|---|
| author | Ramoneda, Pedro Rocamora, Martin Akama, Taketo |
| author_facet | Ramoneda, Pedro Rocamora, Martin Akama, Taketo |
| contents | Autoregressive generative transformers are key in music generation, producing coherent compositions but facing challenges in human-machine collaboration. We propose RefinPaint, an iterative technique that improves the sampling process. It does this by identifying the weaker music elements using a feedback model, which then informs the choices for resampling by an inpainting model. This dual-focus methodology not only facilitates the machine's ability to improve its automatic inpainting generation through repeated cycles but also offers a valuable tool for humans seeking to refine their compositions with automatic proofreading. Experimental results suggest RefinPaint's effectiveness in inpainting and proofreading tasks, demonstrating its value for refining music created by both machines and humans. This approach not only facilitates creativity but also aids amateur composers in improving their work. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_09099 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Music Proofreading with RefinPaint: Where and How to Modify Compositions given Context Ramoneda, Pedro Rocamora, Martin Akama, Taketo Sound Artificial Intelligence Audio and Speech Processing Autoregressive generative transformers are key in music generation, producing coherent compositions but facing challenges in human-machine collaboration. We propose RefinPaint, an iterative technique that improves the sampling process. It does this by identifying the weaker music elements using a feedback model, which then informs the choices for resampling by an inpainting model. This dual-focus methodology not only facilitates the machine's ability to improve its automatic inpainting generation through repeated cycles but also offers a valuable tool for humans seeking to refine their compositions with automatic proofreading. Experimental results suggest RefinPaint's effectiveness in inpainting and proofreading tasks, demonstrating its value for refining music created by both machines and humans. This approach not only facilitates creativity but also aids amateur composers in improving their work. |
| title | Music Proofreading with RefinPaint: Where and How to Modify Compositions given Context |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2407.09099 |