MelodySim: Measuring Melody-aware Music Similarity for Plagiarism Detection
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_ | 1866912717959331840 |
|---|---|
| author | Lu, Tongyu Geist, Charlotta-Marlena Melechovsky, Jan Roy, Abhinaba Herremans, Dorien |
| author_facet | Lu, Tongyu Geist, Charlotta-Marlena Melechovsky, Jan Roy, Abhinaba Herremans, Dorien |
| contents | We propose MelodySim, a melody-aware music similarity model and dataset for plagiarism detection. First, we introduce a novel method to construct a dataset focused on melodic similarity. By augmenting Slakh2100, an existing MIDI dataset, we generate variations of each piece while preserving the melody through modifications such as note splitting, arpeggiation, minor track dropout, and re-instrumentation. A user study confirms that positive pairs indeed contain similar melodies, while other musical tracks are significantly changed. Second, we develop a segment-wise melodic-similarity detection model that uses a MERT encoder and applies a triplet neural network to capture melodic similarity. The resulting decision matrix highlights where plagiarism might occur. The experiments show that our model is able to outperform baseline models in detecting similar melodic fragments on the MelodySim test set. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_20979 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MelodySim: Measuring Melody-aware Music Similarity for Plagiarism Detection Lu, Tongyu Geist, Charlotta-Marlena Melechovsky, Jan Roy, Abhinaba Herremans, Dorien Sound Artificial Intelligence Audio and Speech Processing We propose MelodySim, a melody-aware music similarity model and dataset for plagiarism detection. First, we introduce a novel method to construct a dataset focused on melodic similarity. By augmenting Slakh2100, an existing MIDI dataset, we generate variations of each piece while preserving the melody through modifications such as note splitting, arpeggiation, minor track dropout, and re-instrumentation. A user study confirms that positive pairs indeed contain similar melodies, while other musical tracks are significantly changed. Second, we develop a segment-wise melodic-similarity detection model that uses a MERT encoder and applies a triplet neural network to capture melodic similarity. The resulting decision matrix highlights where plagiarism might occur. The experiments show that our model is able to outperform baseline models in detecting similar melodic fragments on the MelodySim test set. |
| title | MelodySim: Measuring Melody-aware Music Similarity for Plagiarism Detection |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2505.20979 |