{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:19:16Z","timestamp":1775578756550,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci\u00f3n","doi-asserted-by":"publisher","award":["PID2020-118447RA-I00"],"award-info":[{"award-number":["PID2020-118447RA-I00"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681572","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"583-591","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["MUSCAT: A Multimodal mUSic Collection for Automatic Transcription of Real Recordings and Image Scores"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5799-6270","authenticated-orcid":false,"given":"Alejandro","family":"Galan-Cuenca","sequence":"first","affiliation":[{"name":"U.I. for Computing Research, Pattern Recognition and Artificial Intelligence Group, Alicante, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8667-4070","authenticated-orcid":false,"given":"Jose J.","family":"Valero-Mas","sequence":"additional","affiliation":[{"name":"U.I. for Computing Research, Pattern Recognition and Artificial Intelligence Group, Alicante, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5524-2435","authenticated-orcid":false,"given":"Juan C.","family":"Martinez-Sevilla","sequence":"additional","affiliation":[{"name":"U.I. for Computing Research, Pattern Recognition and Artificial Intelligence Group, Alicante, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0767-4290","authenticated-orcid":false,"given":"Antonio","family":"Hidalgo-Centeno","sequence":"additional","affiliation":[{"name":"U.I. for Computing Research, Pattern Recognition and Artificial Intelligence Group, Alicante, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9445-5529","authenticated-orcid":false,"given":"Antonio","family":"Pertusa","sequence":"additional","affiliation":[{"name":"U.I. for Computing Research, Pattern Recognition and Artificial Intelligence Group, Alicante, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3183-2232","authenticated-orcid":false,"given":"Jorge","family":"Calvo-Zaragoza","sequence":"additional","affiliation":[{"name":"U.I. for Computing Research, Pattern Recognition and Artificial Intelligence Group, Alicante, Spain"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447162"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119491"},{"key":"e_1_3_2_1_3_1","volume-title":"Neural Audio-To-Score Music Transcription For Unconstrained Polyphony Using Compact Output Representations","author":"Arroyo V\u00edctor","unstructured":"V\u00edctor Arroyo, Jose J. Valero-Mas, Jorge Calvo-Zaragoza, and Antonio Pertusa. 2022. Neural Audio-To-Score Music Transcription For Unconstrained Polyphony Using Compact Output Representations. In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP. 4603--4607."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2869928"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the 20th International Society for Music Information Retrieval Conference (ISMIR). 99--106","author":"Bittner Rachel M.","year":"2019","unstructured":"Rachel M. Bittner, Magdalena Fuentes, David Rubinstein, Andreas Jansson, Keunwoo Choi, and Thor Kell. 2019. mirdata: Software for Reproducible Usage of Datasets. In Proceedings of the 20th International Society for Music Information Retrieval Conference (ISMIR). 99--106."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397499"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.3390\/app8040606"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-017-5631-y"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Anna-Maria Christodoulou Olivier Lartillot and Alexander Refsum Jensenius. 2024. Multimodal Music Datasets? Challenges and Future Goals in Music Processing. (2024).","DOI":"10.31219\/osf.io\/rs436"},{"key":"e_1_3_2_1_10_1","volume-title":"Towards score following in sheet music images. arXiv preprint arXiv:1612.05050","author":"Dorfer Matthias","year":"2016","unstructured":"Matthias Dorfer, Andreas Arzt, and Gerhard Widmer. 2016. Towards score following in sheet music images. arXiv preprint arXiv:1612.05050 (2016)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5334\/tismir.12"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the 23rd International Society for Music Information Retrieval Conference (ISMIR).","author":"Feffer Michael","year":"2022","unstructured":"Michael Feffer, Chris Donahue, and Zachary Lipton. 2022. Assistive alignment of in-the-wild sheet music and performances. In Proceedings of the 23rd International Society for Music Information Retrieval Conference (ISMIR)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1080\/09298215.2010.523469"},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the 10th International Society for Music Information Retrieval Conference (ISMIR). 645--650","author":"Fremerey Christian","year":"2009","unstructured":"Christian Fremerey, Michael Clausen, Sebastian Ewert, and Meinard M\u00fcller. 2009. Sheet Music-Audio Identification. In Proceedings of the 10th International Society for Music Information Retrieval Conference (ISMIR). 645--650."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/WDM.2003.1233890"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5334\/tismir.31"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616287"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.3389\/fcomp.2021.718340"},{"key":"e_1_3_2_1_20_1","volume-title":"The Humdrum Toolkit. Available online at music-cog. ohio-state. edu\/Humdrum\/index. html","author":"Huron David","year":"1993","unstructured":"David Huron. 1993. The Humdrum Toolkit. Available online at music-cog. ohio-state. edu\/Humdrum\/index. html (1993)."},{"key":"e_1_3_2_1_21_1","volume-title":"Advanced Approaches, and Developments for Creativity","author":"Liu Lele","year":"2021","unstructured":"Lele Liu and Emmanouil Benetos. 2021. From audio to music notation. Handbook of Artificial Intelligence for Music: Foundations, Advanced Approaches, and Developments for Creativity (2021), 693--714."},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the 23rd International Society for Music Information Retrieval Conference (ISMIR). ISMIR, 395--402","author":"Liu Lele","year":"2022","unstructured":"Lele Liu, Qiuqiang Kong, Veronica Morfi, and Emmanouil Benetos. 2022. Performance MIDI-to-score conversion by neural beat tracking. In Proceedings of the 23rd International Society for Music Information Retrieval Conference (ISMIR). ISMIR, 395--402."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413601"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-88"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the XIV Colloquium on Musical Informatics, (CIM)","volume":"1","author":"Nienhuys Han-Wen","year":"2003","unstructured":"Han-Wen Nienhuys and Jan Nieuwenhuizen. 2003. LilyPond, a system for automated music engraving. In Proceedings of the XIV Colloquium on Musical Informatics, (CIM), Vol. 1. 167--171."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2021.4"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR. 25--30","author":"Peeters Geoffroy","year":"2012","unstructured":"Geoffroy Peeters and Kar\u00ebn Fort. 2012. Towards a (Better) Definition of the Description of Annotated MIR Corpora. In Proceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR. 25--30."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86334-0_43"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1561\/9781601988072"},{"key":"e_1_3_2_1_30_1","unstructured":"Xavier Serra Michela Magas Emmanouil Benetos Magdalena Chudy Simon Dixon Arthur Flexer Emilia G\u00f3mez Fabien Gouyon Perfecto Herrera Sergi Jord\u00e0 et al. 2013. Roadmap for music information research. The MIReS Consortium."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMRP.2019.00012"},{"key":"e_1_3_2_1_32_1","volume-title":"ASMD: an automatic framework for compiling multimodal datasets with audio and scores. arXiv preprint arXiv:2003.01958","author":"Simonetta Federico","year":"2020","unstructured":"Federico Simonetta, Stavros Ntalampiras, and Federico Avanzini. 2020. ASMD: an automatic framework for compiling multimodal datasets with audio and scores. arXiv preprint arXiv:2003.01958 (2020)."},{"key":"e_1_3_2_1_33_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems (NeurIPS), Vol. 30 (2017)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5334\/tismir.68"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.02.007"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681572","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681572","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:48Z","timestamp":1750295868000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681572"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":35,"alternative-id":["10.1145\/3664647.3681572","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681572","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}