arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2102.09794cs.SDcs.LGeess.AS
收藏

基于分层循环神经网络的长时程条件旋律生成

Hierarchical Recurrent Neural Networks for Conditional Melody Generation with Long-term Structure

Singapore University of Technology and Design(新加坡科技设计大学)

Zixun Guo, Makris Dimos, Herremans Dorien

摘要:

深度学习技术的兴起迅速推进了许多领域,包括生成音乐系统。存在许多允许生成听起来不错的短片段的系统,然而,这些生成的片段通常缺乏总体的、长期的结构。在这项工作中,我们提出了CM-HRNN:一个有条件的旋律生成模型的基础上分层递归神经网络。这个模型允许我们根据给定的和弦旋律生成具有长期结构的旋律。我们还提出了一种新颖的,简洁的基于事件的表示来编码音乐铅表,同时保留音符的相对位置内的酒吧相对于音乐米。有了这种新的数据表示,所提出的架构可以同时建模的节奏,以及在一个有效的方式的音高结构。所提出的模型产生的旋律进行了广泛的定量实验以及用户研究,以确保输出的音乐质量,以及评估它们是否包含重复模式。我们还将该系统与最先进的AttentionRNN进行了比较。这种比较表明,CM-HRNN生成的旋律包含更多的重复模式(即,较高的压缩比)和较低的色调张力(即,更简洁的音调)。我们的听力测试结果表明,CM-HRNN在长期结构和整体评级方面优于AttentionRNN。

英文摘要:

The rise of deep learning technologies has quickly advanced many fields, including that of generative music systems. There exist a number of systems that allow for the generation of good sounding short snippets, yet, these generated snippets often lack an overarching, longer-term structure. In this work, we propose CM-HRNN: a conditional melody generation model based on a hierarchical recurrent neural network. This model allows us to generate melodies with long-term structures based on given chord accompaniments. We also propose a novel, concise event-based representation to encode musical lead sheets while retaining the notes' relative position within the bar with respect to the musical meter. With this new data representation, the proposed architecture can simultaneously model the rhythmic, as well as the pitch structures in an effective way. Melodies generated by the proposed model were extensively evaluated in quantitative experiments as well as a user study to ensure the musical quality of the output as well as to evaluate if they contain repeating patterns. We also compared the system with the state-of-the-art AttentionRNN. This comparison shows that melodies generated by CM-HRNN contain more repeated patterns (i.e., higher compression ratio) and a lower tonal tension (i.e., more tonally concise). Results from our listening test indicate that CM-HRNN outperforms AttentionRNN in terms of long-term structure and overall rating.

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。

↑