This letter 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 letter 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：

---

用于谐波冲击源分离的对抗性无监督域适应


这封信解决了音乐源分离任务的域适应问题。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和声冲击声源分离模型在不同训练场景下的性能，包括使用两个领域的数据进行监督联合训练以及在一个领域进行预训练并在另一个领域进行微调。我们提出了一种对抗性无监督域适应方法，适用于目标域没有可用标记数据（真实源信号）的情况。通过利用该域中的未标记数据（仅混合数据），实验表明我们的框架可以提高新域上的分离性能，而不会损失原始域上的任何相当大的性能。这封信还介绍了 Tap & Fiddle 数据集，该数据集包含斯堪的纳维亚小提琴曲调的录音以及“脚踏”和“小提琴”的独立曲目。