论文标题
通过明确指导的扩散模型将符号音乐的仪器分离
Instrument Separation of Symbolic Music by Explicitly Guided Diffusion Model
论文作者
论文摘要
与计算机视觉上的着色相似，仪器分离是为了将仪器标签（例如钢琴，吉他...）分配给未标记的混合物的笔记，其中仅包含性能信息。为了解决这个问题，我们采用扩散模型，并明确指导它们以保持混合和音乐之间的一致性。定量结果表明，我们提出的模型可以生成具有创造力的多音阶符号音乐的高保真样本。
Similar to colorization in computer vision, instrument separation is to assign instrument labels (e.g. piano, guitar...) to notes from unlabeled mixtures which contain only performance information. To address the problem, we adopt diffusion models and explicitly guide them to preserve consistency between mixtures and music. The quantitative results show that our proposed model can generate high-fidelity samples for multitrack symbolic music with creativity.
