Current music similarity models typically compute a single, monolithic score, entangling distinct musical dimensions like melody, rhythm, and timbre. This limits user control and interpretability, making it impossible to execute nuanced queries. We introduce MERIT, a framework for learning disentangled, factor-specific music representations tailored to these three core dimensions. To overcome the lack of isolated musical variations in real-world audio, we use a novel training strategy that uses conditional audio generation and source-separated stems to strongly encourage single-factor variation in training data. Our evaluations demonstrate strong factor-wise disentanglement. Each head responds strongly to its intended perceptual dimension while remaining near chance on the others, a representational property that holds across both the synthetic training domain and independent real-world audio.

翻译：当前音乐相似度模型通常计算单一、整体的分数，将旋律、节奏与音色等不同音乐维度纠缠在一起。这限制了用户的可控性与可解释性，使得执行精细化查询成为不可能。我们提出MERIT框架，用于学习针对这三个核心维度解耦的、因子专用的音乐表示。为解决真实音频中缺少隔离化音乐变化的问题，我们采用一种新型训练策略，该策略利用条件音频生成与源分离音轨，强力促进训练数据中的单因子变化。评估结果表明实现了强因子级解耦。每个头均对其目标感知维度反应强烈，而在其他维度上保持近乎随机水平——这一表示特性在合成训练域与独立真实音频中均成立。