{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T20:33:53Z","timestamp":1774730033739,"version":"3.50.1"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031705427","type":"print"},{"value":"9783031705434","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-70543-4_5","type":"book-chapter","created":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T09:02:15Z","timestamp":1725786135000},"page":"74-90","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Enhancing Recognition of\u00a0Historical Musical Pieces with\u00a0Synthetic and\u00a0Composed Images"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2889-9030","authenticated-orcid":false,"given":"Manuel","family":"Villarreal","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0423-2020","authenticated-orcid":false,"given":"Joan Andreu","family":"S\u00e1nchez","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,9]]},"reference":[{"key":"5_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.patrec.2019.02.029","volume":"123","author":"A Bar\u00f3","year":"2019","unstructured":"Bar\u00f3, A., Riba, P., Calvo-Zaragoza, J., Forn\u00e9s, A.: From optical music recognition to handwritten music recognition: A baseline. Pattern Recogn. Lett. 123, 1\u20138 (2019). https:\/\/doi.org\/10.1016\/j.patrec.2019.02.029","journal-title":"Pattern Recogn. Lett."},{"key":"5_CR2","unstructured":"Burgoyne, J., Pugin, L., Eustace, G., Fujinaga, I.: A comparative survey of image binarisation algorithms for optical recognition on degraded musical sources. pp. 509\u2013512 (01 2007)"},{"key":"5_CR3","doi-asserted-by":"publisher","unstructured":"Calvo-Zaragoza, J., Barbancho, I., Tardon, L., Barbancho, A.: Avoiding staff removal stage in optical music recognition: application to scores written in white mensural notation. Formal Pattern Anal. Appl. 18 (09 2014).https:\/\/doi.org\/10.1007\/s10044-014-0415-5","DOI":"10.1007\/s10044-014-0415-5"},{"key":"5_CR4","unstructured":"Calvo-Zaragoza, J., Pacha, A., Shatri, E.: Proceedings of the 5th international workshop on reading music systems (2023)"},{"key":"5_CR5","doi-asserted-by":"publisher","unstructured":"Calvo-Zaragoza, J., Toselli, A.H., Vidal, E.: Early handwritten music recognition with hidden markov models. In: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR). pp. 319\u2013324 (2016).https:\/\/doi.org\/10.1109\/ICFHR.2016.0067","DOI":"10.1109\/ICFHR.2016.0067"},{"key":"5_CR6","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/j.patrec.2019.08.021","volume":"128","author":"J Calvo-Zaragoza","year":"2019","unstructured":"Calvo-Zaragoza, J., Toselli, A.H., Vidal, E.: Handwritten music recognition for mensural notation with convolutional recurrent neural networks. Pattern Recogn. Lett. 128, 115\u2013121 (2019). https:\/\/doi.org\/10.1016\/j.patrec.2019.08.021","journal-title":"Pattern Recogn. Lett."},{"key":"5_CR7","doi-asserted-by":"publisher","unstructured":"Cardoso, J., Capela, A., Rebelo, A., Guedes, C., Costa, J.: Staff detection with stable paths. IEEE transactions on pattern analysis and machine intelligence 31, 1134\u20139 (07 2009).https:\/\/doi.org\/10.1109\/TPAMI.2009.34","DOI":"10.1109\/TPAMI.2009.34"},{"key":"5_CR8","doi-asserted-by":"publisher","unstructured":"Chen, S.F., Goodman, J.: An empirical study of smoothing techniques for language modeling. Comput. Speech Lang. 13(4), 359\u2013394 (1999). https:\/\/doi.org\/10.1006\/csla.1999.0128, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0885230899901286","DOI":"10.1006\/csla.1999.0128"},{"issue":"7","key":"5_CR9","doi-asserted-by":"publisher","first-page":"8227","DOI":"10.1109\/TPAMI.2023.3235826","volume":"45","author":"D Coquenet","year":"2023","unstructured":"Coquenet, D., Chatelain, C., Paquet, T.: Dan: a segmentation-free document attention network for handwritten document recognition. IEEE Trans. Pattern Anal. Mach. Intell. 45(7), 8227\u20138243 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2023.3235826","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"5_CR10","doi-asserted-by":"publisher","unstructured":"Forn\u00e9s, A., Llad\u00f3s, J., S\u00e1nchez, G.: Old handwritten musical symbol classification by a dynamic time warping based method, vol.\u00a05046, pp. 51\u201360, September 2007.https:\/\/doi.org\/10.1007\/978-3-540-88188-9_6","DOI":"10.1007\/978-3-540-88188-9_6"},{"key":"5_CR11","unstructured":"Fujinaga, I.: Salzinnes, CDN-Hsmu M2149.L4, Halifax (Canada), St. Mary\u2019s University - Patrick Power Library, M2149.L4 1554"},{"key":"5_CR12","unstructured":"Gal, Y., Ghahramani, Z.: A theoretically grounded application of dropout in recurrent neural networks. In: NIPS\u201916, pp. 1027\u20131035 (2016)"},{"key":"5_CR13","doi-asserted-by":"publisher","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning, ICML \u201906, pp. 369\u2013376 (2006). https:\/\/doi.org\/10.1145\/1143844.1143891","DOI":"10.1145\/1143844.1143891"},{"key":"5_CR14","doi-asserted-by":"publisher","unstructured":"Hecht-Nielsen: Theory of the backpropagation neural network. In: International 1989 Joint Conference on Neural Networks, pp. 593\u2013605, vol. 1 (1989).https:\/\/doi.org\/10.1109\/IJCNN.1989.118638","DOI":"10.1109\/IJCNN.1989.118638"},{"key":"5_CR15","unstructured":"Henderson, R.: Solmization Syllables in Musical Theory, 1100 to 1600. Columbia University (1969). https:\/\/books.google.es\/books?id=fiufSgAACAAJ"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Kang, L., Riba, P., Wang, Y., Rusi\u00f1ol, M., Forn\u00e9s, A., Villegas, M.: Ganwriting: Content-conditioned generation of styled handwritten word images (2020)","DOI":"10.1007\/978-3-030-58592-1_17"},{"key":"5_CR17","unstructured":"Kim, G., et al.: Donut: document understanding transformer without ocr. arXiv preprint arXiv:2111.15664, 7, 15 (2021)"},{"key":"5_CR18","doi-asserted-by":"publisher","unstructured":"Martinez\u00a0Sevilla, J., R\u00edos\u00a0Vila, A., Castellanos, F., Calvo-Zaragoza, J.: A Holistic Approach for Aligned Music and Lyrics Transcription, pp. 185\u2013201, August 2023. https:\/\/doi.org\/10.1007\/978-3-031-41676-7_11","DOI":"10.1007\/978-3-031-41676-7_11"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Nikolaidou, K., et al.: Wordstylist: Styled verbatim handwritten text generation with latent diffusion models (2023)","DOI":"10.1007\/978-3-031-41679-8_22"},{"key":"5_CR20","doi-asserted-by":"publisher","unstructured":"Pondenkandath, V., Alberti, M., Diatta, M., Ingold, R., Liwicki, M.: Historical document synthesis with generative adversarial networks. In: 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW), vol.\u00a05, pp. 146\u2013151 (2019).https:\/\/doi.org\/10.1109\/ICDARW.2019.40096","DOI":"10.1109\/ICDARW.2019.40096"},{"key":"5_CR21","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents (2022)"},{"key":"5_CR22","doi-asserted-by":"publisher","unstructured":"Rebelo, A., Fujinaga, I., Paszkiewicz, F., Mar\u00e7al, A., Guedes, C., Cardoso, J.: Optical music recognition: state-of-the-art and open issues. Int. J. Multimed. Inf. Retrieval 1, October 2012. https:\/\/doi.org\/10.1007\/s13735-012-0004-6","DOI":"10.1007\/s13735-012-0004-6"},{"key":"5_CR23","unstructured":"R\u00edos-Vila, A., I\u00f1esta, J.M., Calvo-Zaragoza, J.: End-to-end full-page optical music recognition for mensural notation. In: Ismir 2022 Hybrid Conference (2022)"},{"key":"5_CR24","doi-asserted-by":"publisher","first-page":"470","DOI":"10.1007\/978-3-031-04881-4_37","volume-title":"Pattern Recognition and Image Analysis","author":"A R\u00edos-Vila","year":"2022","unstructured":"R\u00edos-Vila, A., I\u00f1esta, J.M., Calvo-Zaragoza, J.: On the use of transformers for end-to-end optical music recognition. In: Pinho, A.J., Georgieva, P., Teixeira, L.F., S\u00e1nchez, J.A. (eds.) Pattern Recognition and Image Analysis, pp. 470\u2013481. Springer, Cham (2022)"},{"key":"5_CR25","doi-asserted-by":"publisher","unstructured":"Rossant, F., Isabelle, B.: Robust and adaptive omr system including fuzzy modeling, fusion of musical rules, and possible error detection. EURASIP J. Adv. Signal Process. 2007 (01 2007). https:\/\/doi.org\/10.1155\/2007\/81541","DOI":"10.1155\/2007\/81541"},{"key":"5_CR26","doi-asserted-by":"publisher","unstructured":"Tanha, J., Does, J., Depuydt, K., S\u00e1nchez, J.: Crossing the lines: making optimal use of context in line-based handwritten text recognition. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 956\u2013960 (2015). https:\/\/doi.org\/10.1109\/ICDAR.2015.7333903","DOI":"10.1109\/ICDAR.2015.7333903"},{"key":"5_CR27","doi-asserted-by":"publisher","unstructured":"Torras, P., Bar\u00f3, A., Kang, L., Forn\u00e9s, A.: On the integration of language models into sequence to sequence architectures for handwritten music recognition. In: Proceedings of the 22nd International Society for Music Information Retrieval Conference, pp. 690\u2013696 (2021).https:\/\/doi.org\/10.5281\/zenodo.5624451","DOI":"10.5281\/zenodo.5624451"},{"key":"5_CR28","unstructured":"Vaswani, A., et al.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"key":"5_CR29","doi-asserted-by":"publisher","unstructured":"Villarreal, M., S\u00e1nchez, J.A.: Handwritten music recognition improvement through language model re-interpretation for mensural notation. In: 2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 199\u2013204 (2020).https:\/\/doi.org\/10.1109\/ICFHR2020.2020.00045","DOI":"10.1109\/ICFHR2020.2020.00045"},{"key":"5_CR30","unstructured":"Williams, R.J., Zipser, D.: Gradient-Based Learning Algorithms for Recurrent Networks and Their Computational Complexity, pp. 433\u2013486 (1995)"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70543-4_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,18]],"date-time":"2025-02-18T14:06:51Z","timestamp":1739887611000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70543-4_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705427","9783031705434"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70543-4_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"9 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Athens","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2024.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}