Generating Separated Singing Vocals Using a Diffusion Model Conditioned on Music Mixtures
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911288200790016 |
|---|---|
| author | Plaja-Roglans, Genís Hung, Yun-Ning Serra, Xavier Pereira, Igor |
| author_facet | Plaja-Roglans, Genís Hung, Yun-Ning Serra, Xavier Pereira, Igor |
| contents | Separating the individual elements in a musical mixture is an essential process for music analysis and practice. While this is generally addressed using neural networks optimized to mask or transform the time-frequency representation of a mixture to extract the target sources, the flexibility and generalization capabilities of generative diffusion models are giving rise to a novel class of solutions for this complicated task. In this work, we explore singing voice separation from real music recordings using a diffusion model which is trained to generate the solo vocals conditioned on the corresponding mixture. Our approach improves upon prior generative systems and achieves competitive objective scores against non-generative baselines when trained with supplementary data. The iterative nature of diffusion sampling enables the user to control the quality-efficiency trade-off, and also refine the output when needed. We present an ablation study of the sampling algorithm, highlighting the effects of the user-configurable parameters. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_21342 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Generating Separated Singing Vocals Using a Diffusion Model Conditioned on Music Mixtures Plaja-Roglans, Genís Hung, Yun-Ning Serra, Xavier Pereira, Igor Sound Artificial Intelligence Separating the individual elements in a musical mixture is an essential process for music analysis and practice. While this is generally addressed using neural networks optimized to mask or transform the time-frequency representation of a mixture to extract the target sources, the flexibility and generalization capabilities of generative diffusion models are giving rise to a novel class of solutions for this complicated task. In this work, we explore singing voice separation from real music recordings using a diffusion model which is trained to generate the solo vocals conditioned on the corresponding mixture. Our approach improves upon prior generative systems and achieves competitive objective scores against non-generative baselines when trained with supplementary data. The iterative nature of diffusion sampling enables the user to control the quality-efficiency trade-off, and also refine the output when needed. We present an ablation study of the sampling algorithm, highlighting the effects of the user-configurable parameters. |
| title | Generating Separated Singing Vocals Using a Diffusion Model Conditioned on Music Mixtures |
| topic | Sound Artificial Intelligence |
| url | https://arxiv.org/abs/2511.21342 |