Article: Using generative adversarial network for music transformation Journal: International Journal of Computational Science and Engineering (IJCSE) 2025 Vol.28 No.6 pp.638 - 649 Abstract: In this study, we propose a generative adversarial network (GAN) framework for music style transfer. Initially, a dataset of traditional Jiangnan songs is pre-processed into two categories: complete compositions and corresponding musical phrases (starting and ending notes), which are then converted into piano-roll images. The CycleGAN model is then used to train these images until the model converges to establish a music style transfer model. The goal is to allow users to input only the starting and ending notes of each measure as a musical phrase, and the system will convert this phrase into complete musical compositions in the Jiangnan style. Then we use a deep learning framework and music expertise for data processing, enhancing the quality and utility of our conversions. At the same time, we have established music style assessment metrics based on the statistical data of the dataset, providing an effective method for evaluating music styles. Inderscience Publishers - linking academia, business and industry through research

Title: Using generative adversarial network for music transformation

Authors: Cheng-Han Wu; Yu-Cheng Lin; Pimpa Cheewaprakobkit; Wan-Chin Ting; Timothy K. Shih

Addresses: Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan ' Department of Computer Science and Engineering, Yuan Ze University, Taoyuan, Taiwan ' Department of Information Technology, Asia-Pacific International University, Saraburi 18180, Thailand ' Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan ' Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan

Abstract: In this study, we propose a generative adversarial network (GAN) framework for music style transfer. Initially, a dataset of traditional Jiangnan songs is pre-processed into two categories: complete compositions and corresponding musical phrases (starting and ending notes), which are then converted into piano-roll images. The CycleGAN model is then used to train these images until the model converges to establish a music style transfer model. The goal is to allow users to input only the starting and ending notes of each measure as a musical phrase, and the system will convert this phrase into complete musical compositions in the Jiangnan style. Then we use a deep learning framework and music expertise for data processing, enhancing the quality and utility of our conversions. At the same time, we have established music style assessment metrics based on the statistical data of the dataset, providing an effective method for evaluating music styles.

Keywords: music transformation; generative adversarial network; GAN; automatic music generation; music style transfer.

DOI: 10.1504/IJCSE.2025.149758

International Journal of Computational Science and Engineering, 2025 Vol.28 No.6, pp.638 - 649

Received: 08 Apr 2024
Accepted: 22 Jul 2024
Published online: 12 Nov 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Using generative adversarial network for music transformation

Keep up-to-date