{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/symbolic-music-genre-transfer-with-cyclegan","title":"Symbolic Music Genre Transfer with CycleGAN","arxiv_id":"1809.07575","date":"2018-09-20","proceeding":null,"authors":["Gino Brunner","Yuyi Wang","Roger Wattenhofer","Sumu Zhao"],"abstract":"Deep generative models such as Variational Autoencoders (VAEs) and Generative\nAdversarial Networks (GANs) have recently been applied to style and domain\ntransfer for images, and in the case of VAEs, music. GAN-based models employing\nseveral generators and some form of cycle consistency loss have been among the\nmost successful for image domain transfer. In this paper we apply such a model\nto symbolic music and show the feasibility of our approach for music genre\ntransfer. Evaluations using separate genre classifiers show that the style\ntransfer works well. In order to improve the fidelity of the transformed music,\nwe add additional discriminators that cause the generators to keep the\nstructure of the original music mostly intact, while still achieving strong\ngenre transfer. Visual and audible results further show the potential of our\napproach. To the best of our knowledge, this paper represents the first\napplication of GANs to symbolic music domain transfer.","url_abs":"http://arxiv.org/abs/1809.07575v1","url_pdf":"http://arxiv.org/pdf/1809.07575v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"symbolic-music-genre-transfer-with-cyclegan","repo_url":"https://github.com/sumuzhao/CycleGAN-Music-Style-Transfer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"symbolic-music-genre-transfer-with-cyclegan","repo_url":"https://github.com/Git-Uzair/Piano-Genre-Transfer-CycleGan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"symbolic-music-genre-transfer-with-cyclegan","repo_url":"https://github.com/khornlund/CycleGAN-Music-Style-Transfer-1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"symbolic-music-genre-transfer-with-cyclegan","repo_url":"https://github.com/milesigel/audio-sentiment-transfer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"symbolic-music-genre-transfer-with-cyclegan","repo_url":"https://github.com/sumuzhao/CycleGAN-Music-Style-Transfer-Refactorization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"music-genre-transfer","task_name":"Music Genre Transfer"},{"task_slug":"style-transfer","task_name":"Style Transfer"}],"methods":[{"method_slug":"cycle-consistency-loss","method_name":"Cycle Consistency Loss"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1809.07575","atlas_url":"https://app.syntology.ai/?focus=1809.07575","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}