Semantic-Aware Interpretable Multimodal Music Auto-Tagging
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_ | 1866914605851213824 |
|---|---|
| author | Patakis, Andreas Lyberatos, Vassilis Kantarelis, Spyridon Dervakos, Edmund Stamou, Giorgos |
| author_facet | Patakis, Andreas Lyberatos, Vassilis Kantarelis, Spyridon Dervakos, Edmund Stamou, Giorgos |
| contents | Music auto-tagging is essential for organizing and discovering music in extensive digital libraries. While foundation models achieve exceptional performance in this domain, their outputs often lack interpretability, limiting trust and usability for researchers and end-users alike. In this work, we present an interpretable framework for music auto-tagging that leverages groups of musically meaningful multimodal features, derived from signal processing, deep learning, ontology engineering, and natural language processing. To enhance interpretability, we cluster features semantically and employ an expectation maximization algorithm, assigning distinct weights to each group based on its contribution to the tagging process. Our method achieves competitive tagging performance while offering a deeper understanding of the decision-making process, paving the way for more transparent and user-centric music tagging systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_17233 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Semantic-Aware Interpretable Multimodal Music Auto-Tagging Patakis, Andreas Lyberatos, Vassilis Kantarelis, Spyridon Dervakos, Edmund Stamou, Giorgos Machine Learning Sound Audio and Speech Processing Music auto-tagging is essential for organizing and discovering music in extensive digital libraries. While foundation models achieve exceptional performance in this domain, their outputs often lack interpretability, limiting trust and usability for researchers and end-users alike. In this work, we present an interpretable framework for music auto-tagging that leverages groups of musically meaningful multimodal features, derived from signal processing, deep learning, ontology engineering, and natural language processing. To enhance interpretability, we cluster features semantically and employ an expectation maximization algorithm, assigning distinct weights to each group based on its contribution to the tagging process. Our method achieves competitive tagging performance while offering a deeper understanding of the decision-making process, paving the way for more transparent and user-centric music tagging systems. |
| title | Semantic-Aware Interpretable Multimodal Music Auto-Tagging |
| topic | Machine Learning Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2505.17233 |