arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2409.08155eess.AS
收藏

基于图神经网络的分层符号流行音乐生成

Hierarchical Symbolic Pop Music Generation with Graph Neural Networks

Wen Qing Lim, Jinhua Liang, Huan Zhang

AI总结:

针对现有图相关音乐生成研究少、复调音乐生成未考虑长时结构的问题,提出基于多图表示的两步法,用两个变分自编码器分别生成乐句与歌曲结构,可学习音乐结构细节。

摘要:

音乐本质上由复杂结构构成,将其表示为图有助于捕捉多层级的关系。尽管研究人员已使用多种深度生成技术探索音乐生成,但与图相关的音乐生成研究仍较为匮乏。早期基于图的音乐生成仅能生成旋律,而近期生成复调音乐的研究未考虑长时结构。本文探索了一种多图方法,用于表示华语流行音乐的节奏模式与乐句结构。据此,我们提出一种两步法,旨在生成具备连贯节奏与长时结构的复调音乐。我们训练了两个变分自编码器(Variational Auto-Encoder)网络:一个在MIDI数据集上训练以生成4小节乐句,另一个基于歌曲结构标签训练以生成完整歌曲结构。研究表明,模型能够学习训练数据集中的大部分结构细微差异,包括和弦与音高频率分布,以及乐句属性。

英文摘要:

Music is inherently made up of complex structures, and representing them as graphs helps to capture multiple levels of relationships. While music generation has been explored using various deep generation techniques, research on graph-related music generation is sparse. Earlier graph-based music generation worked only on generating melodies, and recent works to generate polyphonic music do not account for longer-term structure. In this paper, we explore a multi-graph approach to represent both the rhythmic patterns and phrase structure of Chinese pop music. Consequently, we propose a two-step approach that aims to generate polyphonic music with coherent rhythm and long-term structure. We train two Variational Auto-Encoder networks - one on a MIDI dataset to generate 4-bar phrases, and another on song structure labels to generate full song structure. Our work shows that the models are able to learn most of the structural nuances in the training dataset, including chord and pitch frequency distributions, and phrase attributes.

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。

↑