剖析自监督音乐模型各层特征，揭示其任务适配机制
Layer-wise Investigation of Large-Scale Self-Supervised Music Representation Models
- 逐层分析音乐模型的表征能力，识别不同层的任务专属性
- 验证自监督模型在多个下游任务中的性能优势
- 指导用户选择最优层以提升特定任务表现
基于自监督学习（SSL）的预训练音乐信息检索模型近年来广受欢迎，在多种下游任务中表现优异。然而，对编码信息的具体含义及其适用性的研究仍不充分。本研究聚焦先进音乐表示模型MusicFM与新兴SSL模型MuQ，从三个方面展开分析：(i) 验证SSL模型在多任务中的优势；(ii) 探索各层信息对不同任务的专属性；(iii) 比较不同层选择带来的性能差异。研究揭示了SSL模型在音乐信息检索中的结构特性与潜在应用方向。
原文摘要 · Abstract (English)
Recently, pre-trained models for music information retrieval based on self-supervised learning (SSL) are becoming popular, showing success in various downstream tasks. However, there is limited research on the specific meanings of the encoded information and their applicability. Exploring these aspects can help us better understand their capabilities and limitations, leading to more effective use in downstream tasks. In this study, we analyze the advanced music representation model MusicFM and the newly emerged SSL model MuQ. We focus on three main aspects: (i) validating the advantages of SSL models across multiple downstream tasks, (ii) exploring the specialization of layer-wise information for different tasks, and (iii) comparing performance differences when selecting specific layers. Through this analysis, we reveal insights into the structure and potential applications of SSL models in music information retrieval.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。