This paper addresses the problem of domain adaptation for the task of music source separation. Using datasets from two different domains, we compare the performance of a deep learning-based harmonic-percussive source separation model under different training scenarios, including supervised joint training using data from both domains and pre-training in one domain with fine-tuning in another. We propose an adversarial unsupervised domain adaptation approach suitable for the case where no labelled data (ground-truth source signals) from a target domain is available. By leveraging unlabelled data (only mixtures) from this domain, experiments show that our framework can improve separation performance on the new domain without losing any considerable performance on the original domain. The paper also introduces the Tap & Fiddle dataset, a dataset containing recordings of Scandinavian fiddle tunes along with isolated tracks for 'foot-tapping' and 'violin'.

中文翻译：

---

对抗性无监督域自适应，用于谐波打击源分离

本文针对音乐源分离任务解决了域自适应问题。使用来自两个不同领域的数据集，我们比较了基于深度学习的谐波打击源分离模型在不同训练场景下的性能，包括使用来自两个领域的数据进行有监督的联合训练以及在一个领域进行预训练而在另一个领域进行微调。我们提出一种对抗性无监督域自适应方法，适用于没有来自目标域的标记数据（真相源信号）可用的情况。通过利用来自该域的未标记数据（仅混合），实验表明我们的框架可以提高新域的分离性能，而不会损失原始域的任何性能。本文还介绍了Tap＆Fiddle数据集，