Since most of music has repetitive structures from motifs to phrases, repeating musical ideas can be a basic operation for music composition. The basic block that we focus on is conceptualized as loops which are essential ingredients of music. Furthermore, meaningful note patterns can be formed in a finite space, so it is sufficient to represent them with combinations of discrete symbols as done in other domains. In this work, we propose symbolic music loop generation via learning discrete representations. We first extract loops from MIDI datasets using a loop detector and then learn an autoregressive model trained by discrete latent codes of the extracted loops. We show that our model outperforms well-known music generative models in terms of both fidelity and diversity, evaluating on random space. Our code and supplementary materials are available at https://github.com/sjhan91/Loop_VQVAE_Official.

翻译：由于大多数音乐都有从调时到短语的重复结构,重复音乐思想可以成为音乐构成的基本操作。我们关注的基本块块被概念化为是音乐基本成分的循环。此外,在有限的空间中可以形成有意义的笔记模式,这样就足以以与其他领域一样的离散符号组合来代表它们。在这项工作中,我们建议通过学习离散表达方式来产生象征性的音乐循环。我们首先使用循环探测器从MIDI数据集中提取回路,然后学习一种由提取回路的离散潜伏代码训练的自动递增模型。我们显示,我们的模型在真实性和多样性两方面都超越了众所周知的音乐基因化模型,对随机空间进行评估。我们的代码和补充材料可在https://github.com/sjhan91/Loop_VVAE_OPOOO上查阅。