SteerMusic: Enhanced Musical Consistency for Zero-shot Text-guided and Personalized Music Editing
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908695251648512 |
|---|---|
| author | Niu, Xinlei Cheuk, Kin Wai Zhang, Jing Murata, Naoki Lai, Chieh-Hsin Mancusi, Michele Choi, Woosung Fabbro, Giorgio Liao, Wei-Hsiang Martin, Charles Patrick Mitsufuji, Yuki |
| author_facet | Niu, Xinlei Cheuk, Kin Wai Zhang, Jing Murata, Naoki Lai, Chieh-Hsin Mancusi, Michele Choi, Woosung Fabbro, Giorgio Liao, Wei-Hsiang Martin, Charles Patrick Mitsufuji, Yuki |
| contents | Music editing is an important step in music production, which has broad applications, including game development and film production. Most existing zero-shot text-guided editing methods rely on pretrained diffusion models by involving forward-backward diffusion processes. However, these methods often struggle to preserve the musical content. Additionally, text instructions alone usually fail to accurately describe the desired music. In this paper, we propose two music editing methods that improve the consistency between the original and edited music by leveraging score distillation. The first method, SteerMusic, is a coarse-grained zero-shot editing approach using delta denoising score. The second method, SteerMusic+, enables fine-grained personalized music editing by manipulating a concept token that represents a user-defined musical style. SteerMusic+ allows for the editing of music into user-defined musical styles that cannot be achieved by the text instructions alone. Experimental results show that our methods outperform existing approaches in preserving both music content consistency and editing fidelity. User studies further validate that our methods achieve superior music editing quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_10826 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SteerMusic: Enhanced Musical Consistency for Zero-shot Text-guided and Personalized Music Editing Niu, Xinlei Cheuk, Kin Wai Zhang, Jing Murata, Naoki Lai, Chieh-Hsin Mancusi, Michele Choi, Woosung Fabbro, Giorgio Liao, Wei-Hsiang Martin, Charles Patrick Mitsufuji, Yuki Sound Multimedia Audio and Speech Processing Music editing is an important step in music production, which has broad applications, including game development and film production. Most existing zero-shot text-guided editing methods rely on pretrained diffusion models by involving forward-backward diffusion processes. However, these methods often struggle to preserve the musical content. Additionally, text instructions alone usually fail to accurately describe the desired music. In this paper, we propose two music editing methods that improve the consistency between the original and edited music by leveraging score distillation. The first method, SteerMusic, is a coarse-grained zero-shot editing approach using delta denoising score. The second method, SteerMusic+, enables fine-grained personalized music editing by manipulating a concept token that represents a user-defined musical style. SteerMusic+ allows for the editing of music into user-defined musical styles that cannot be achieved by the text instructions alone. Experimental results show that our methods outperform existing approaches in preserving both music content consistency and editing fidelity. User studies further validate that our methods achieve superior music editing quality. |
| title | SteerMusic: Enhanced Musical Consistency for Zero-shot Text-guided and Personalized Music Editing |
| topic | Sound Multimedia Audio and Speech Processing |
| url | https://arxiv.org/abs/2504.10826 |