In this paper, we introduce the MoisesDB dataset for musical source separation. It consists of 240 tracks from 45 artists, covering twelve musical genres. For each song, we provide its individual audio sources, organized in a two-level hierarchical taxonomy of stems. This will facilitate building and evaluating fine-grained source separation systems that go beyond the limitation of using four stems (drums, bass, other, and vocals) due to lack of data. To facilitate the adoption of this dataset, we publish an easy-to-use Python library to download, process and use MoisesDB. Alongside a thorough documentation and analysis of the dataset contents, this work provides baseline results for open-source separation models for varying separation granularities (four, five, and six stems), and discuss their results.

本文介绍了用于音乐源分离的MoisesDB数据集，包括240首歌曲，来自45位艺术家，覆盖了十二种音乐流派。我们提供了每首歌曲的个体音频源，以两级分层分类法进行组织。为了方便构建和评估细粒度的源分离系统，我们发布了一个易于使用的Python库来下载、处理和使用MoisesDB。除了详细介绍和分析数据集内容外，本研究还提供了针对不同分离粒度（四、五和六个音频源）的开源分离模型的基线结果，并讨论了它们的结果。

Moisesdb: 超越4音轨的源分离数据集