When Counterpoint Meets Chinese Folk Melodies
When Counterpoint Meets Chinese Folk Melodies
复制标题
DOI：
--
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Nan Jiang;Sheng Jin;Z. Duan;Changshui Zhang
中科院分区：
文献类型：
--
作者：
Nan Jiang;Sheng Jin;Z. Duan;Changshui Zhang
对位是西方音乐理论中的一个重要概念。在过去的一个世纪里，人们对将复调融入中国民间音乐创作产生了浓厚的兴趣。在本文中，我们提出了一个基于强化学习的系统FolkDuet，用于在线生成中国民间旋律的对旋律。在没有中国民间二重唱的现有数据的情况下，FolkDuet采用了两种基于域外数据的奖励模式，即巴赫合唱团和单声中国民间旋律。互动奖励模型针对巴赫合唱团外部形成的二重唱进行训练，以模拟对位互动；风格奖励模型针对中国民歌的单音旋律进行训练，以模拟旋律模式。有了这两个奖励，FolkDuet的生成者被训练成在保持中国民间风格的同时产生反旋律。整个生成过程以在线方式进行，允许实时互动的人机二重奏即兴表演。实验表明，该算法取得了比基线更好的主客观结果。
Counterpoint is an important concept in Western music theory. In the past century, there have been significant interests in incorporating counterpoint into Chinese folk music composition. In this paper, we propose a reinforcement learning-based system, named FolkDuet, towards the online countermelody generation for Chinese folk melodies. With no existing data of Chinese folk duets, FolkDuet employs two reward models based on out-of-domain data i.e., Bach chorales, and monophonic Chinese folk melodies. An interaction reward model is trained on the duets formed from outer parts of Bach chorales to model counterpoint interaction, while a style reward model is trained on monophonic melodies of Chinese folk songs to model melodic patterns. With both rewards, the generator of FolkDuet is trained to generate countermelodies while maintaining the Chinese folk style. The entire generation process is performed in an online fashion, allowing real-time interactive human-machine duet improvisation. Experiments show that the proposed algorithm achieves better subjective and objective results than the baselines.