arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.13840eess.AS
收藏

音乐表征的半监督对比学习

Semi-Supervised Contrastive Learning of Musical Representations

Julien Guinot, Elio Quinton, György Fazekas

AI总结:

本文提出半监督对比学习(SemiSupCon),通过融合监督与自监督目标,利用少量标注数据注入音乐知识,提升下游MIR任务性能与鲁棒性,并在音高、调性估计及自动标注中表现优异。

摘要:

尽管对比学习在音乐信息检索中取得了成功,但对比自监督固有的模糊性带来了挑战。仅依赖增强链和自监督正样本采样策略,可能导致预训练目标无法捕获下游任务所需的关键音乐信息。我们引入了半监督对比学习(SemiSupCon),一种在音乐表征对比学习中利用音乐信息标注数据(监督信号)的简单方法。我们的方法通过将监督和自监督对比目标结合在一个比先前方法更简单的框架中,将音乐相关的监督信号引入自监督对比学习。该框架在具有中等数量标注数据的多个下游MIR任务上,提升了下游性能和对抗音频损坏的鲁棒性。我们的方法能够通过选择标注数据来塑造学习到的相似度度量,这些数据(1)将音乐领域知识注入表征中,并且(2)以最小的通用下游性能损失提升域外性能。我们在音乐相关但非平凡相似的任务(如音高和调性估计)上展示了强大的迁移学习性能。此外,我们的方法在自动标注任务上,相较于自监督方法,仅使用预训练中5%的可用标签即实现了性能提升。

英文摘要:

Despite the success of contrastive learning in Music Information Retrieval, the inherent ambiguity of contrastive self-supervision presents a challenge. Relying solely on augmentation chains and self-supervised positive sampling strategies can lead to a pretraining objective that does not capture key musical information for downstream tasks. We introduce semi-supervised contrastive learning (SemiSupCon), a simple method for leveraging musically informed labeled data (supervision signals) in the contrastive learning of musical representations. Our approach introduces musically relevant supervision signals into self-supervised contrastive learning by combining supervised and self-supervised contrastive objectives in a simpler framework than previous approaches. This framework improves downstream performance and robustness to audio corruptions on a range of downstream MIR tasks with moderate amounts of labeled data. Our approach enables shaping the learned similarity metric through the choice of labeled data that (1) infuses the representations with musical domain knowledge and (2) improves out-of-domain performance with minimal general downstream performance loss. We show strong transfer learning performance on musically related yet not trivially similar tasks - such as pitch and key estimation. Additionally, our approach shows performance improvement on automatic tagging over self-supervised approaches with only 5\% of available labels included in pretraining.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑