Assessing Data Replication in Symbolic Music via Adapted Structural Similarity Index Measure
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_ | 1866914041653362688 |
|---|---|
| author | Ji, Shulei Wang, Zihao Ma, Le Yu, Jiaxing Zhang, Kejun |
| author_facet | Ji, Shulei Wang, Zihao Ma, Le Yu, Jiaxing Zhang, Kejun |
| contents | AI-generated music may inadvertently replicate samples from the training data, raising concerns of plagiarism. Similarity measures can quantify such replication, thereby offering supervision and guidance for music generation models. Existing similarity measure methods for symbolic music mainly target melody repetition, leaving a gap in assessing complex music with rich textures and expressive performance characteristics. To address this gap, we introduce SSIMuse, the first adaptation of the Structural Similarity Index Measure (SSIM) from images to symbolic music. Specifically, we represent symbolic music as image-like piano rolls in binary and velocity-based forms. Build upon these representations, we reinterprete and suitably modify the SSIM components in the musical context to develop two variants, i.e., SSIMuse-B and SSIMuse-V, for evaluating data replication in composition and dynamic performance, respectively. Controlled experiments on synthetic samples from multiple datasets show that SSIMuse can reliably detect exact replication at a granularity of at least one bar. SSIMuse enables open evaluation of replication in music generation and draws attention to its broader ethical, social, legal, and economic implications. The code is available at https://github.com/Tayjsl97/SSIMuse. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_13658 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Assessing Data Replication in Symbolic Music via Adapted Structural Similarity Index Measure Ji, Shulei Wang, Zihao Ma, Le Yu, Jiaxing Zhang, Kejun Audio and Speech Processing AI-generated music may inadvertently replicate samples from the training data, raising concerns of plagiarism. Similarity measures can quantify such replication, thereby offering supervision and guidance for music generation models. Existing similarity measure methods for symbolic music mainly target melody repetition, leaving a gap in assessing complex music with rich textures and expressive performance characteristics. To address this gap, we introduce SSIMuse, the first adaptation of the Structural Similarity Index Measure (SSIM) from images to symbolic music. Specifically, we represent symbolic music as image-like piano rolls in binary and velocity-based forms. Build upon these representations, we reinterprete and suitably modify the SSIM components in the musical context to develop two variants, i.e., SSIMuse-B and SSIMuse-V, for evaluating data replication in composition and dynamic performance, respectively. Controlled experiments on synthetic samples from multiple datasets show that SSIMuse can reliably detect exact replication at a granularity of at least one bar. SSIMuse enables open evaluation of replication in music generation and draws attention to its broader ethical, social, legal, and economic implications. The code is available at https://github.com/Tayjsl97/SSIMuse. |
| title | Assessing Data Replication in Symbolic Music via Adapted Structural Similarity Index Measure |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2509.13658 |