We present COCOLA (Coherence-Oriented Contrastive Learning for Audio), a
contrastive learning method for musical audio representations that captures the
harmonic and rhythmic coherence between samples. Our method operates at the
level of stems (or their combinations) composing music tracks and allows the
objective evaluation of compositional models for music in the task of
accompaniment generation. We also introduce a new baseline for compositional
music generation called CompoNet, based on ControlNet \cite{zhang2023adding},
generalizing the tasks of MSDM, and quantify it against the latter using
COCOLA. We release all models trained on public datasets containing separate
stems (MUSDB18-HQ, MoisesDB, Slakh2100, and CocoChorales).

COCOLA 是一种用于音乐音频表示的对比学习方法，捕捉样本之间的和谐和节奏的一致性，目的在于对音乐作品的组合模型进行伴奏生成的客观评估。我们还引入了基于 ControlNet 的音乐组合生成新基准 CompoNet，并使用 COCOLA 与 ControlNet 进行量化比较。我们公开发布了在包含不同音轨的公共数据集（MUSDB18-HQ、MoisesDB、Slakh2100 和 CocoChorales）上训练的所有模型。