SongBench: A Fine-Grained Multi-Aspect Benchmark for Song Quality Assessment
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913070713929728 |
|---|---|
| author | Wu, Dapeng Lei, Shun Tan, Wei Li, Guangzheng Wang, Yunzhe Zhang, Huaicheng Zuo, Lishi Wu, Zhiyong |
| author_facet | Wu, Dapeng Lei, Shun Tan, Wei Li, Guangzheng Wang, Yunzhe Zhang, Huaicheng Zuo, Lishi Wu, Zhiyong |
| contents | Recent advancements in Text-to-Song generation have enabled realistic musical content production, yet existing evaluation benchmarks lack the professional granularity to capture multi-dimensional aesthetic nuances. In this paper, we propose SongBench, a specialized framework for fine-grained song assessment across seven key dimensions: Vocal, Instrument, Melody, Structure, Arrangement, Mixing, and Musicality. Utilizing this framework, we construct an expert-annotated database comprising 11,717 samples from state-of-the-art models, labeled by music professionals. Extensive experimental results demonstrate that SongBench achieves high correlation with expert ratings. By revealing fine-grained performance gaps in current state-of-the-art models, SongBench serves as a diagnostic benchmark to steer the development toward more professional and musically coherent song generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_25937 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SongBench: A Fine-Grained Multi-Aspect Benchmark for Song Quality Assessment Wu, Dapeng Lei, Shun Tan, Wei Li, Guangzheng Wang, Yunzhe Zhang, Huaicheng Zuo, Lishi Wu, Zhiyong Audio and Speech Processing Artificial Intelligence Sound Recent advancements in Text-to-Song generation have enabled realistic musical content production, yet existing evaluation benchmarks lack the professional granularity to capture multi-dimensional aesthetic nuances. In this paper, we propose SongBench, a specialized framework for fine-grained song assessment across seven key dimensions: Vocal, Instrument, Melody, Structure, Arrangement, Mixing, and Musicality. Utilizing this framework, we construct an expert-annotated database comprising 11,717 samples from state-of-the-art models, labeled by music professionals. Extensive experimental results demonstrate that SongBench achieves high correlation with expert ratings. By revealing fine-grained performance gaps in current state-of-the-art models, SongBench serves as a diagnostic benchmark to steer the development toward more professional and musically coherent song generation. |
| title | SongBench: A Fine-Grained Multi-Aspect Benchmark for Song Quality Assessment |
| topic | Audio and Speech Processing Artificial Intelligence Sound |
| url | https://arxiv.org/abs/2604.25937 |