基于生成对抗网络的智能音乐制作综述.

Recently,researchers pay more and more attentions for automatic or semi-automatic music generation based on computer algorithm.With the further development of deep learning,researchers start to focus on producing high-quality and multifarious-style music with neural network and priori knowledge of music theory.Furthermore,several works introduced generative adversarial network(GAN) to try to improve the quality of the results.To summarize the important results in this area is meaningful and with guiding significance for the following works.This paper firstly reviewed the history of intelligent music,then listed related GAN model that are commonly applied in music creation,after that it analyzed some important works in this area.Finally,it presented some observations,and prospected future work direction. [ABSTRACT FROM AUTHOR]