基于Transformer的多轨音乐生成对抗网络  

Multi-track music generative adversarial network based on Transformer

作　　者：汪涛 靳聪[2] 李小兵[3] 帖云 齐林[1] WANG Tao;JIN Cong;LI Xiaobing;TIE Yun;QI Lin(School of Information Engineering,Zhengzhou University,Zhengzhou Henan 450001,China;School of Information and Communication Engineering,Communication University of China,Beijing 100024,China;Central Conservatory of Music,Beijing 100031,China)

机构地区：[1]郑州大学信息工程学院,郑州450001 [2]中国传媒大学信息与通信工程学院,北京100024 [3]中央音乐学院,北京100031

出　　处：《计算机应用》2021年第12期3585-3589,共5页journal of Computer Applications

基　　金：国家重点研发计划项目(2018YFB1403900);中央高校基本科研业务费专项资金资助项目(CUC210B011)。

摘　　要：符号音乐的生成在人工智能领域中仍然是一个尚未解决的问题,面临着诸多挑战。经研究发现,现有的多音轨音乐生成方法在旋律、节奏及和谐度上均达不到市场所要求的效果,并且生成的音乐大多不符合基础的乐理知识。为了解决以上问题,提出一种新颖的基于Transformer的多音轨音乐生成对抗网络(Transformer-GAN),以乐理规则为指导来产生具有高音乐性的音乐作品。首先,采用Transformer的译码部分与在Transformer基础之上改编的Cross-TrackTransformer(CT-Transformer)分别对单音轨内部及多音轨之间的信息进行学习;然后,使用乐理规则和交叉熵损失相结合的方法引导生成网络的训练,并在训练鉴别网络的同时优化精心设计的目标损失函数;最后,生成具有旋律性、节奏性及和谐性的多音轨音乐作品。实验结果表明,与其他多乐器音乐生成模型相比,在钢琴轨、吉他轨及贝斯轨上,Transformer-GAN的预测精确度(PA)最低分别提升了12%、11%及22%,序列相似度(SS)最低分别提升了13%、6%及10%,休止符指标最低分别提升了8%、4%及17%。由此可见,Transformer-GAN在加入了CTTransformer及音乐规则奖励模块之后能有效提升音乐的PA、SS等指标,使生成的音乐质量整体上有较大的提升。Symbolic music generation is still an unsolved problem in the field of artificial intelligence and faces many challenges.It has been found that the existing methods for generating polyphonic music fail to meet the marke requirements in terms of melody,rhythm and harmony,and most of the generated music does not conform to basic music theory knowledge.In order to solve the above problems,a new Transformer-based multi-track music Generative Adversarial Network(Transformer-GAN)was proposed to generate music with high musicality under the guidance of music rules.Firstly,the decoding part of Transformer and the Cross-Track Transformer(CT-Transformer)adapted on the basis of Transformer were used to learn the information within a single track and between multiple tracks respectively.Then,a combination of music rules and cross-entropy loss was employed to guide the training of the generative network,and the well-designed objective loss function was optimized while training the discriminative network.Finally,multi-track music works with melody,rhythm and harmony were generated.Experimental results show that compared with other multi-instrument music generation models,for piano,guitar and bass tracks,Transformer-GAN improves Prediction Accuracy(PA)by a minimum of 12%,11%and 22%,improves Sequence Similarity(SS)by a minimum of 13%,6%and 10%,and improves the rest index by a minimum of 8%,4%and 17%.It can be seen that Transformer-GAN can effectively improve the indicators including PA and SS of music after adding CT-Transformer and music rule reward module,which leads to a relatively high overall improvement of the generated music.

关 键 词：音乐生成 TRANSFORMER 音乐规则 目标损失函数 对抗网络 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]