A transformer generative adversarial network for multi-track music generation

Cong Jin; Tao Wang; Xiaobing Li; Chu Jie Jiessie Tie; Yun Tie; Shan Liu; Ming Yan; Yongzhi Li; Junxian Wang; Shenze Huang

首页> 中文期刊> 《智能技术学报》 >A transformer generative adversarial network for multi-track music generation

A transformer generative adversarial network for multi-track music generation

开具论文收录证明 >>

期刊封面封底目录下载 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

This study proposes a new generation network based on transformers and guided by the music theory to produce high-quality music work.In this study,the decoding block of the transformer is used to learn the internal information of single-track music,and cross-track transformers are used to learn the information amongst the tracks of different musical instruments.A reward network based on the music theory is proposed,which optimizes the global and local loss objective functions while training and discriminating the network so that the reward network can provide a reliable adjustment method for the generation of the network.The method of combining the reward network and cross entropy loss is used to guide the training of the generator and produce high-quality music work.Compared with other multi-track music generation models,the experimental results verify the validity of the model.

著录项

来源
《智能技术学报》 |2022年第3期|369-380|共12页
作者
Cong Jin; Tao Wang; Xiaobing Li; Chu Jie Jiessie Tie; Yun Tie; Shan Liu; Ming Yan; Yongzhi Li; Junxian Wang; Shenze Huang;
展开▼
作者单位

School of Information and Communication Engineering University of China;

School of Information and Engineering University;

Central Conservatory of Music;

Department of computer Science of Toronto;

School of Data Science and Media Intelligence University of China;

School of Light Industry and Engineering China University of Technology;

School of Animation and Digital Arts University of China;

展开▼
原文格式 PDF
正文语种 chi
中图分类 TN9;
关键词
artificial intelligence; deep learning; MULTIMEDIA;

相似文献

中文文献
外文文献
专利

1. Optimized Generative Adversarial Networks for Adversarial Sample Generation [J] . Daniyal M.Alghazzawi ,Syed Hamid Hasan ,Surbhi Bhatia . 计算机、材料和连续体(英文) . 2022,第8期
2. Emotional dialog generation via multiple classifiers based on a generative adversarial network [J] . Wei CHEN ,Xinmiao CHEN ,Xiao SUN . 虚拟现实与智能硬件(中英文) . 2021,第1期
3. Research on clothing patterns generation based on multi-scales self-attention improved generative adversarial network [J] . Zi-yan Yu ,Tian-jian Luo . 智能计算与控制论国际期刊(英文) . 2021,第4期
4. GAN-GLS:Generative Lyric Steganography Based on Generative Adversarial Networks [J] . Cuilin Wang ,Yuling Liu ,Yongju Tong . 计算机、材料和连续体(英文) . 2021,第10期
5. RGB--to--NIR Image Translation Using Generative Adversarial Network [A] . Yi Huang . 2020

A transformer generative adversarial network for multi-track music generation

摘要

著录项

相似文献

相关主题

期刊订阅