融合对比与重建，让音乐表示既保真又解耦。
Balancing Information Preservation and Disentanglement in Self-Supervised Music Representation Learning
- 多视角自监督框架，联合对比与重建目标。
- 结合两者可有效解耦音乐属性且不损失信息完整性。
- 适合研究音乐表征学习或音频生成的学者。
近期自监督学习（SSL）方法为无标注音乐音频提供了多种有用表征提取策略。部分技术侧重通过重建保留完整细节，另一些则通过对比目标强调语义结构。但很少有工作在统一框架中探讨这两种范式的交互。本文提出一种多视角自监督框架，用于解耦音乐音频表征，同时结合对比与重建目标。该架构旨在提升解耦子空间中信息保真度与结构化语义。我们在受控环境中对对比策略的设计选择进行了广泛评估，发现尽管重建与对比策略存在一致权衡，但有效结合时能相互补充，实现音乐属性解耦而不牺牲信息完整性。
原文摘要 · Abstract (English)
Recent advances in self-supervised learning (SSL) methods offer a range of strategies for capturing useful representations from music audio without the need for labeled data. While some techniques focus on preserving comprehensive details through reconstruction, others favor semantic structure via contrastive objectives. Few works examine the interaction between these paradigms in a unified SSL framework. In this work, we propose a multi-view SSL framework for disentangling music audio representations that combines contrastive and reconstructive objectives. The architecture is designed to promote both information fidelity and structured semantics of factors in disentangled subspaces. We perform an extensive evaluation on the design choices of contrastive strategies using music audio representations in a controlled setting. We find that while reconstruction and contrastive strategies exhibit consistent trade-offs, when combined effectively, they complement each other; this enables the disentanglement of music attributes without compromising information integrity.
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。