{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T04:52:39Z","timestamp":1783572759140,"version":"3.55.0"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032093707","type":"print"},{"value":"9783032093714","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-09371-4_5","type":"book-chapter","created":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T23:50:21Z","timestamp":1767311421000},"page":"67-81","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["GAN-Based Content-Conditioned Generation of\u00a0Handwritten Musical Symbols"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3316-5463","authenticated-orcid":false,"given":"Gerard","family":"Asbert","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0327-9046","authenticated-orcid":false,"given":"Pau","family":"Torras","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1962-3916","authenticated-orcid":false,"given":"Lei","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9692-5336","authenticated-orcid":false,"given":"Alicia","family":"Forn\u00e9s","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4533-4739","authenticated-orcid":false,"given":"Josep","family":"Llad\u00f3s","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"5_CR1","doi-asserted-by":"publisher","unstructured":"Bar\u00f3, A., Badal, C., Forn\u00eas, A.: Handwritten historical music recognition by sequence-to-sequence with attention mechanism. In: 2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 205\u2013210, September 2020. https:\/\/doi.org\/10.1109\/ICFHR2020.2020.00046","DOI":"10.1109\/ICFHR2020.2020.00046"},{"key":"5_CR2","unstructured":"Bi\u0144kowski, M., Sutherland, D.J., Arbel, M., Gretton, A.: Demystifying mmd gans. arXiv e-prints pp. arXiv\u20131801 (2018)"},{"key":"5_CR3","unstructured":"Bond-Taylor, S., Leach, A., Long, Y., Willcocks, C.G.: Deep generative modelling: A comparative review of vaes, gans, normalizing flows, energy-based and autoregressive models. CoRR abs\/2103.04922 (2021). https:\/\/arxiv.org\/abs\/2103.04922"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Calvo-Zaragoza, J., Jr, J.H., Pacha, A.: Understanding optical music recognition. ACM Comput. Surv. (CSUR) 53(4), 1\u201335 (2020)","DOI":"10.1145\/3397499"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Calvo-Zaragoza, J., Oncina, J.: Recognition of pen-based music notation: the homus dataset. In: 2014 22nd International Conference on Pattern Recognition, pp. 3038\u20133043. IEEE (2014)","DOI":"10.1109\/ICPR.2014.524"},{"key":"5_CR6","unstructured":"Calvo-Zaragoza, J., Rizo, D., Quereda, J.M.I.: Two (note) heads are better than one: Pen-based multimodal interaction with music scores. In: ISMIR, pp. 509\u2013514 (2016)"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Elanwar, R., Betke, M.: Generative adversarial networks for handwriting image generation: a review. The Visual Computer, pp. 1\u201324 (2024)","DOI":"10.1007\/s00371-024-03534-9"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Forn\u00e9s, A., Llad\u00f3s, J., S\u00e1nchez, G.: Old handwritten musical symbol classification by a dynamic time warping based method. In: International Workshop on Graphics Recognition, pp. 51\u201360. Springer (2007)","DOI":"10.1007\/978-3-540-88188-9_6"},{"issue":"11","key":"5_CR9","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020). https:\/\/doi.org\/10.1145\/3422622","journal-title":"Commun. ACM"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Haji\u010d, J., Pecina, P.: The muscima++ dataset for handwritten optical music recognition. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol.\u00a01, pp. 39\u201346. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.16"},{"key":"5_CR11","unstructured":"Havelka, J., Mayer, J., Pecina, P.: Symbol generation via autoencoders for handwritten music synthesis. In: Proc. 5th Int. Workshop on Reading Music Systems, p.\u00a020 (2023)"},{"key":"5_CR12","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems 30 (2017)"},{"key":"5_CR13","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol.\u00a033, pp. 6840\u20136851. Curran Associates, Inc. (2020)"},{"issue":"12","key":"5_CR14","doi-asserted-by":"publisher","first-page":"8846","DOI":"10.1109\/TPAMI.2021.3122572","volume":"44","author":"L Kang","year":"2022","unstructured":"Kang, L., Riba, P., Rusi\u00f1ol, M., Forn\u00e9s, A., Villegas, M.: Content and style aware generation of text-line images for handwriting recognition. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 8846\u20138860 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2021.3122572","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"5_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/978-3-030-58592-1_17","volume-title":"Computer Vision \u2013 ECCV 2020","author":"L Kang","year":"2020","unstructured":"Kang, L., Riba, P., Wang, Y., Rusi\u00f1ol, M., Forn\u00e9s, A., Villegas, M.: GANwriting: content-conditioned generation of styled handwritten word images. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12368, pp. 273\u2013289. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58592-1_17"},{"key":"5_CR16","doi-asserted-by":"publisher","unstructured":"Kingma, D.P., Welling, M.: Auto-Encoding Variational Bayes, December 2022. https:\/\/doi.org\/10.48550\/arXiv.1312.6114","DOI":"10.48550\/arXiv.1312.6114"},{"key":"5_CR17","doi-asserted-by":"publisher","unstructured":"Makhzani, A., Shlens, J., Jaitly, N., Goodfellow, I., Frey, B.: Adversarial Autoencoders. arXiv preprint arXiv:1511.05644 (arXiv:1511.05644) (May 2016). https:\/\/doi.org\/10.48550\/arXiv.1511.05644","DOI":"10.48550\/arXiv.1511.05644"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Mayer, J., Pecina, P.: Synthesizing training data for handwritten music recognition. In: International Conference on Document Analysis and Recognition, pp. 626\u2013641. Springer (2021)","DOI":"10.1007\/978-3-030-86334-0_41"},{"key":"5_CR19","doi-asserted-by":"publisher","unstructured":"Mehmood, R., Bashir, R., Giri, K.: Deep generative models: A review. Indian J. Sci. Technol. 16, 460\u2013467 (2023). https:\/\/doi.org\/10.17485\/IJST\/v16i7.2296","DOI":"10.17485\/IJST\/v16i7.2296"},{"key":"5_CR20","unstructured":"Pippi, V., Quattrini, F., Cascianelli, S., Cucchiara, R.: Hwd: A novel evaluation score for styled handwritten text generation. arXiv e-prints pp. arXiv\u20132310 (2023)"},{"key":"5_CR21","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1007\/s13735-012-0004-6","volume":"1","author":"A Rebelo","year":"2012","unstructured":"Rebelo, A., Fujinaga, I., Paszkiewicz, F., Marcal, A.R., Guedes, C., Cardoso, J.S.: Optical music recognition: state-of-the-art and open issues. Int. J. Multimed. Inf. Retrieval 1, 173\u2013190 (2012)","journal-title":"Int. J. Multimed. Inf. Retrieval"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Shatri, E., Palavala, K.R., Fazekas, G.: Synthesising handwritten music with gans: a comprehensive evaluation of cyclewgan, progan, and dcgan. In: 2024 IEEE International Conference on Big Data (BigData), pp. 3208\u20133217. IEEE (2024)","DOI":"10.1109\/BigData62323.2024.10825834"},{"key":"5_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2009\/843401","volume":"2009","author":"LJ Tard\u00f3n","year":"2009","unstructured":"Tard\u00f3n, L.J., Sammartino, S., Barbancho, I., G\u00f3mez, V., Oliver, A.: Optical music recognition for scores written in white mensural notation. EURASIP J. Image Video Process. 2009, 1\u201323 (2009)","journal-title":"EURASIP J. Image Video Process."},{"key":"5_CR24","unstructured":"Tirupati, N., Shatri, E., Fazekas, G., et\u00a0al.: Crafting handwritten notations: Towards sheet music generation. In: Proc. 5th Int. Workshop on Reading Music Systems (2024)"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Torras, P., Biswas, S., Forn\u00e9s, A.: A unified representation framework for the evaluation of optical music recognition systems. Int. J. Document Anal. Recogn. (IJDAR) 27(3), 379\u2013393 (2024)","DOI":"10.1007\/s10032-024-00485-8"},{"key":"5_CR26","doi-asserted-by":"publisher","unstructured":"Zdenek, J., Nakayama, H.: JokerGAN: memory-efficient model for handwritten text generation with text line awareness. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 5655\u20135663. MM \u201921. Association for Computing Machinery, New York, October 2021. https:\/\/doi.org\/10.1145\/3474085.3475713","DOI":"10.1145\/3474085.3475713"},{"key":"5_CR27","doi-asserted-by":"publisher","unstructured":"Zdenek, J., Nakayama, H.: Handwritten text generation with character-specific encoding for style imitation. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) Document Analysis and Recognition - ICDAR 2023, pp. 313\u2013329. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41679-8_18","DOI":"10.1007\/978-3-031-41679-8_18"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2025 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-09371-4_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T23:50:22Z","timestamp":1767311422000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-09371-4_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032093707","9783032093714"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-09371-4_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"Link to the GAN code:\n                      \n                      Link to the custom Smashcima code:","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code Availability"}},{"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":"Wuhan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iapr.org\/icdar2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}