arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.00212cs.SDcs.AIeess.ASstat.ML
收藏

流行音乐Transformer:基于节拍的表现性流行钢琴作品的建模与生成

Pop Music Transformer: Beat-based Modeling and Generation of Expressive Pop Piano Compositions

Taiwan AI Labs(台湾人工智能实验室);Academia Sinica(中央研究院)

Yu-Siang Huang, Yi-Hsuan Yang

摘要:

最近已经提出了大量基于深度学习的模型用于自动音乐合成。在这些模型中,Transformer脱颖而出,作为一个突出的方法,产生表现力的古典钢琴演奏与连贯的结构长达一分钟。该模型的强大之处在于它可以自己学习数据的抽象,而不需要太多人为强加的领域知识或约束。与这种一般的方法相比,本文表明,Transformers可以做得更好的音乐建模,当我们改进的方式将乐谱转换成数据馈送到一个Transformer模型。特别地,我们试图在输入数据中施加韵律结构,使得Transformers可以更容易地意识到音乐中的节拍-小节-短语层次结构。新的数据表示保持了本地节奏变化的灵活性,并提供了控制音乐的节奏和和声结构的障碍。通过这种方法,我们构建了一个流行音乐Transformer,它比现有的Transformer模型具有更好的节奏结构。

英文摘要:

A great number of deep learning based models have been recently proposed for automatic music composition. Among these models, the Transformer stands out as a prominent approach for generating expressive classical piano performance with a coherent structure of up to one minute. The model is powerful in that it learns abstractions of data on its own, without much human-imposed domain knowledge or constraints. In contrast with this general approach, this paper shows that Transformers can do even better for music modeling, when we improve the way a musical score is converted into the data fed to a Transformer model. In particular, we seek to impose a metrical structure in the input data, so that Transformers can be more easily aware of the beat-bar-phrase hierarchical structure in music. The new data representation maintains the flexibility of local tempo changes, and provides hurdles to control the rhythmic and harmonic structure of music. With this approach, we build a Pop Music Transformer that composes Pop piano music with better rhythmic structure than existing Transformer models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑