{"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/music-transcription-modelling-and-composition","title":"Music transcription modelling and composition using deep learning","arxiv_id":"1604.08723","date":"2016-04-29","proceeding":null,"authors":["Bob L. Sturm","João Felipe Santos","Oded Ben-Tal","Iryna Korshunova"],"abstract":"We apply deep learning methods, specifically long short-term memory (LSTM)\nnetworks, to music transcription modelling and composition. We build and train\nLSTM networks using approximately 23,000 music transcriptions expressed with a\nhigh-level vocabulary (ABC notation), and use them to generate new\ntranscriptions. Our practical aim is to create music transcription models\nuseful in particular contexts of music composition. We present results from\nthree perspectives: 1) at the population level, comparing descriptive\nstatistics of the set of training transcriptions and generated transcriptions;\n2) at the individual level, examining how a generated transcription reflects\nthe conventions of a music practice in the training transcriptions (Celtic\nfolk); 3) at the application level, using the system for idea generation in\nmusic composition. We make our datasets, software and sound examples open and\navailable: \\url{https://github.com/IraKorshunova/folk-rnn}.","url_abs":"http://arxiv.org/abs/1604.08723v1","url_pdf":"http://arxiv.org/pdf/1604.08723v1.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":"music-transcription-modelling-and-composition","repo_url":"https://github.com/IraKorshunova/folk-rnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"music-transcription-modelling-and-composition","repo_url":"https://github.com/9552nZ/SmartSheetMusic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"music-transcription-modelling-and-composition","repo_url":"https://github.com/pskiers/symbotunes","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"descriptive","task_name":"Descriptive"},{"task_slug":"music-transcription","task_name":"Music Transcription"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1604.08723","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}