{"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/lead-sheet-generation-and-arrangement-by","title":"Lead Sheet Generation and Arrangement by Conditional Generative Adversarial Network","arxiv_id":"1807.11161","date":"2018-07-30","proceeding":null,"authors":["Hao-Min Liu","Yi-Hsuan Yang"],"abstract":"Research on automatic music generation has seen great progress due to the\ndevelopment of deep neural networks. However, the generation of\nmulti-instrument music of arbitrary genres still remains a challenge. Existing\nresearch either works on lead sheets or multi-track piano-rolls found in MIDIs,\nbut both musical notations have their limits. In this work, we propose a new\ntask called lead sheet arrangement to avoid such limits. A new recurrent\nconvolutional generative model for the task is proposed, along with three new\nsymbolic-domain harmonic features to facilitate learning from unpaired lead\nsheets and MIDIs. Our model can generate lead sheets and their arrangements of\neight-bar long. Audio samples of the generated result can be found at\nhttps://drive.google.com/open?id=1c0FfODTpudmLvuKBbc23VBCgQizY6-Rk","url_abs":"http://arxiv.org/abs/1807.11161v1","url_pdf":"http://arxiv.org/pdf/1807.11161v1.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":"lead-sheet-generation-and-arrangement-by","repo_url":"https://github.com/liuhaumin/LeadsheetArrangement","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"lead-sheet-generation-and-arrangement-by","repo_url":"https://github.com/liuhaumin/leadsheetgan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"music-generation","task_name":"Music Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}