Temporal Adaptation of Pre-trained Foundation Models for Music Structure Analysis
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_ | 1866918096979099648 |
|---|---|
| author | Zhang, Yixiao Chen, Haonan Wang, Ju-Chiang Chen, Jitong |
| author_facet | Zhang, Yixiao Chen, Haonan Wang, Ju-Chiang Chen, Jitong |
| contents | Audio-based music structure analysis (MSA) is an essential task in Music Information Retrieval that remains challenging due to the complexity and variability of musical form. Recent advances highlight the potential of fine-tuning pre-trained music foundation models for MSA tasks. However, these models are typically trained with high temporal feature resolution and short audio windows, which limits their efficiency and introduces bias when applied to long-form audio. This paper presents a temporal adaptation approach for fine-tuning music foundation models tailored to MSA. Our method enables efficient analysis of full-length songs in a single forward pass by incorporating two key strategies: (1) audio window extension and (2) low-resolution adaptation. Experiments on the Harmonix Set and RWC-Pop datasets show that our method significantly improves both boundary detection and structural function prediction, while maintaining comparable memory usage and inference speed. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_13572 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Temporal Adaptation of Pre-trained Foundation Models for Music Structure Analysis Zhang, Yixiao Chen, Haonan Wang, Ju-Chiang Chen, Jitong Sound Audio and Speech Processing Audio-based music structure analysis (MSA) is an essential task in Music Information Retrieval that remains challenging due to the complexity and variability of musical form. Recent advances highlight the potential of fine-tuning pre-trained music foundation models for MSA tasks. However, these models are typically trained with high temporal feature resolution and short audio windows, which limits their efficiency and introduces bias when applied to long-form audio. This paper presents a temporal adaptation approach for fine-tuning music foundation models tailored to MSA. Our method enables efficient analysis of full-length songs in a single forward pass by incorporating two key strategies: (1) audio window extension and (2) low-resolution adaptation. Experiments on the Harmonix Set and RWC-Pop datasets show that our method significantly improves both boundary detection and structural function prediction, while maintaining comparable memory usage and inference speed. |
| title | Temporal Adaptation of Pre-trained Foundation Models for Music Structure Analysis |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2507.13572 |