TY  - JOUR
T1  - Polyphonic Music Generation with Sequence Generative Adversarial Networks
AU  - Lee, Sang-gil 
AU  - Hwang, Uiwon 
AU  - Min, Seonwoo 
AU  - Yoon, Sungroh 
JO  - Journal of KIISE, JOK
PY  - 2024
DA  - 2024/1/14
DO  - 10.5626/JOK.2024.51.1.78
KW  - music generation
KW  - generative adversarial network
KW  - reinforcement learning
KW  - deep generative model
KW  - deep learning
AB  - In this paper, we propose an application of sequence generative adversarial networks (SeqGAN) for generating polyphonic musical sequences. We introduce a representation of polyphonic MIDI files that could encapsulate both chords and melodies with dynamic timings. This method condensed the duration, octaves, and keys of both melodies and chords into a single word vector representation. Our generator composed of recurrent neural networks was trained to predict distributions of musical word sequences. Additionally, we employed the least square loss function for the discriminator to stabilize training of the model. Our model could create sequences that are musically coherent. It exhibited improved quantitative and qualitative measures.