{"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/optical-music-recognition-with-convolutional","title":"Optical Music Recognition with Convolutional Sequence-to-Sequence Models","arxiv_id":"1707.04877","date":"2017-07-16","proceeding":null,"authors":["Eelco van der Wel","Karen Ullrich"],"abstract":"Optical Music Recognition (OMR) is an important technology within Music\nInformation Retrieval. Deep learning models show promising results on OMR\ntasks, but symbol-level annotated data sets of sufficient size to train such\nmodels are not available and difficult to develop. We present a deep learning\narchitecture called a Convolutional Sequence-to-Sequence model to both move\ntowards an end-to-end trainable OMR pipeline, and apply a learning process that\ntrains on full sentences of sheet music instead of individually labeled\nsymbols. The model is trained and evaluated on a human generated data set, with\nvarious image augmentations based on real-world scenarios. This data set is the\nfirst publicly available set in OMR research with sufficient size to train and\nevaluate deep learning models. With the introduced augmentations a pitch\nrecognition accuracy of 81% and a duration accuracy of 94% is achieved,\nresulting in a note level accuracy of 80%. Finally, the model is compared to\ncommercially available methods, showing a large improvements over these\napplications.","url_abs":"http://arxiv.org/abs/1707.04877v1","url_pdf":"http://arxiv.org/pdf/1707.04877v1.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":"optical-music-recognition-with-convolutional","repo_url":"https://github.com/eelcovdw/mono-musicxml-dataset","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"optical-music-recognition-with-convolutional","repo_url":"https://github.com/GaetanBaert/OMR_deep","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"optical-music-recognition-with-convolutional","repo_url":"https://github.com/apacha/OMR-Datasets","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"music-information-retrieval","task_name":"Music Information Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}