Paper Info
Title
A GAN Model With Self-attention Mechanism To Generate Multi-instruments Symbolic Music
Abstract
GAN has recently been proved to be able to generate symbolic music in the form of piano-rolls. However, those existing GAN-based multi-track music generation methods are always unstable. Moreover, due to defects in the temporal features extraction, the generated multi-track music does not sound natural enough. Therefore, we propose a new GAN model with self-attention mechanism, DMB-GAN, which can extract more temporal features of music to generate multi-instruments music stably. First of all, to generate more consistent and natural single-track music, we introduce self-attention mechanism to enable GAN-based music generation model to extract not only spatial features but also temporal features. Secondly, to generate multi-instruments music with harmonic structure among all tracks, we construct a dual generative adversarial architecture with multi-branches, each branch for one track. Finally, to improve generated quality of multi-instruments symbolic music, we introduce switchable normalization to stabilize network training. The experimental results show that DMB-GAN can stably generate coherent, natural multi-instruments music with good quality.
Year
DOI
Venue
2019
10.1109/IJCNN.2019.8852291
2019 International Joint Conference on Neural Networks (IJCNN)
Keywords
Field
DocType
symbolic music generation,Generative Adversarial Networks,multi-instruments,switchable normalization,self-attention mechanism
Music generation,Architecture,Normalization (statistics),Pattern recognition,Computer science,Harmonic structure,Speech recognition,Artificial intelligence,Generative grammar
Conference
ISSN
ISBN
Citations 
2161-4393
978-1-7281-1986-1
1
PageRank 
References 
Authors
0.37
0
3
Name
Order
Citations
PageRank
Faqian Guan110.37
Chun Yu2153.65
Suqiong Yang310.37