Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ru, Ganghui, Wang, Jieying, Zhao, Jiahao, Wu, Yulun, Yu, Yi, Jiang, Nannan, Wang, Wei, Li, Wei
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2508.09788
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912577469022208
author Ru, Ganghui
Wang, Jieying
Zhao, Jiahao
Wu, Yulun
Yu, Yi
Jiang, Nannan
Wang, Wei
Li, Wei
author_facet Ru, Ganghui
Wang, Jieying
Zhao, Jiahao
Wu, Yulun
Yu, Yi
Jiang, Nannan
Wang, Wei
Li, Wei
contents Fine-tuning pre-trained foundation models has made significant progress in music information retrieval. However, applying these models to beat tracking tasks remains unexplored as the limited annotated data renders conventional fine-tuning methods ineffective. To address this challenge, we propose HingeNet, a novel and general parameter-efficient fine-tuning method specifically designed for beat tracking tasks. HingeNet is a lightweight and separable network, visually resembling a hinge, designed to tightly interface with pre-trained foundation models by using their intermediate feature representations as input. This unique architecture grants HingeNet broad generalizability, enabling effective integration with various pre-trained foundation models. Furthermore, considering the significance of harmonics in beat tracking, we introduce harmonic-aware mechanism during the fine-tuning process to better capture and emphasize the harmonic structures in musical signals. Experiments on benchmark datasets demonstrate that HingeNet achieves state-of-the-art performance in beat and downbeat tracking
format Preprint
id arxiv_https___arxiv_org_abs_2508_09788
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HingeNet: A Harmonic-Aware Fine-Tuning Approach for Beat Tracking
Ru, Ganghui
Wang, Jieying
Zhao, Jiahao
Wu, Yulun
Yu, Yi
Jiang, Nannan
Wang, Wei
Li, Wei
Sound
Audio and Speech Processing
Fine-tuning pre-trained foundation models has made significant progress in music information retrieval. However, applying these models to beat tracking tasks remains unexplored as the limited annotated data renders conventional fine-tuning methods ineffective. To address this challenge, we propose HingeNet, a novel and general parameter-efficient fine-tuning method specifically designed for beat tracking tasks. HingeNet is a lightweight and separable network, visually resembling a hinge, designed to tightly interface with pre-trained foundation models by using their intermediate feature representations as input. This unique architecture grants HingeNet broad generalizability, enabling effective integration with various pre-trained foundation models. Furthermore, considering the significance of harmonics in beat tracking, we introduce harmonic-aware mechanism during the fine-tuning process to better capture and emphasize the harmonic structures in musical signals. Experiments on benchmark datasets demonstrate that HingeNet achieves state-of-the-art performance in beat and downbeat tracking
title HingeNet: A Harmonic-Aware Fine-Tuning Approach for Beat Tracking
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2508.09788