{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T17:16:52Z","timestamp":1742923012372,"version":"3.40.3"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031377303"},{"type":"electronic","value":"9783031377310"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-37731-0_6","type":"book-chapter","created":{"date-parts":[[2023,8,9]],"date-time":"2023-08-09T14:02:30Z","timestamp":1691589750000},"page":"64-77","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal Strategies for\u00a0Image and\u00a0Audio Music Transcription: A Comparative Study"],"prefix":"10.1007","author":[{"given":"Mar\u00eda","family":"Alfaro-Contreras","sequence":"first","affiliation":[]},{"given":"Jose J.","family":"Valero-Mas","sequence":"additional","affiliation":[]},{"given":"Jos\u00e9 M.","family":"I\u00f1esta","sequence":"additional","affiliation":[]},{"given":"Jorge","family":"Calvo-Zaragoza","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,10]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Alfaro-Contreras, M., Valero-Mas, J.J., I\u00f1esta, J.M., Calvo-Zaragoza, J.: Insights into transfer learning between image and audio music transcription. In: Proceedings of the 19th Sound and Music Computing Conference (Accepted). Axea sas\/SMC Network (2022)","DOI":"10.1016\/j.eswa.2022.119491"},{"issue":"1","key":"6_CR2","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1109\/MSP.2018.2869928","volume":"36","author":"E Benetos","year":"2018","unstructured":"Benetos, E., Dixon, S., Duan, Z., Ewert, S.: Automatic music transcription: an overview. IEEE Signal Process. Mag. 36(1), 20\u201330 (2018)","journal-title":"IEEE Signal Process. Mag."},{"issue":"4","key":"6_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3397499","volume":"53","author":"J Calvo-Zaragoza","year":"2020","unstructured":"Calvo-Zaragoza, J., Haji\u010d, J., Jr., Pacha, A.: Understanding optical music recognition. ACM Comput. Surv. (CSUR) 53(4), 1\u201335 (2020)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Calvo-Zaragoza, J., Rizo, D.: Camera-PrIMuS: neural end-to-end optical music recognition on realistic monophonic scores. In: Proceedings of the 19th International Society for Music Information Retrieval Conference, Paris, France, pp. 248\u2013255 (2018)","DOI":"10.3390\/app8040606"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Dumas, B., Signer, B., Lalanne, D.: Fusion in multimodal interactive systems: an HMM-based algorithm for user-induced adaptation. In: Proceedings of the 4th ACM SIGCHI Symposium on Engineering Interactive Computing Systems, pp. 15\u201324 (2012)","DOI":"10.1145\/2305484.2305490"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"de la Fuente, C., Valero-Mas, J.J., Castellanos, F.J., Calvo-Zaragoza, J.: Multimodal image and audio music transcription. Int. J. Multimedia Inf. Retrieval 1\u20138 (2021)","DOI":"10.1007\/s13735-021-00221-6"},{"key":"6_CR7","doi-asserted-by":"crossref","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 2006, pp. 369\u2013376. ACM, New York (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"6_CR8","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7\u20139 May 2015, Conference Track Proceedings (2015)"},{"issue":"8","key":"6_CR9","first-page":"707","volume":"10","author":"VI Levenshtein","year":"1966","unstructured":"Levenshtein, V.I.: Binary codes capable of correcting deletions, insertions, and reversals. Soviet physics doklady 10(8), 707\u2013710 (1966)","journal-title":"Soviet physics doklady"},{"key":"6_CR10","doi-asserted-by":"publisher","first-page":"693","DOI":"10.1007\/978-3-030-72116-9_24","volume-title":"Handbook of Artificial Intelligence for Music","author":"L Liu","year":"2021","unstructured":"Liu, L., Benetos, E.: From audio to music notation. In: Miranda, E.R. (ed.) Handbook of Artificial Intelligence for Music, pp. 693\u2013714. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-72116-9_24"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Liu, L., Morfi, V., Benetos, E.: Joint multi-pitch detection and score transcription for polyphonic piano music. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 281\u2013285. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9413601"},{"key":"6_CR12","series-title":"The Springer Series on Challenges in Machine Learning","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1007\/978-3-319-57021-1_16","volume-title":"Gesture Recognition","author":"V Pitsikalis","year":"2017","unstructured":"Pitsikalis, V., Katsamanis, A., Theodorakis, S., Maragos, P.: Multimodal gesture recognition via multiple hypotheses rescoring. In: Escalera, S., Guyon, I., Athitsos, V. (eds.) Gesture Recognition. TSSCML, pp. 467\u2013496. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-57021-1_16"},{"key":"6_CR13","unstructured":"Rom\u00e1n, M.A., Pertusa, A., Calvo-Zaragoza, J.: A holistic approach to polyphonic music transcription with neural networks. In: Proceedings of the 20th International Society for Music Information Retrieval Conference, Delft, The Netherlands, pp. 731\u2013737 (2019)"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Simonetta, F., Ntalampiras, S., Avanzini, F.: Multimodal music information processing and retrieval: survey and future challenges. In: 2019 International Workshop on Multilayer Music Representation and Processing (MMRP), pp. 10\u201318. IEEE (2019)","DOI":"10.1109\/MMRP.2019.00012"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Singh, A., Sangwan, A., Hansen, J.H.: Improved parcel sorting by combining automatic speech and character recognition. In: 2012 IEEE International Conference on Emerging Signal Processing Applications, pp. 52\u201355. IEEE (2012)","DOI":"10.1109\/ESPA.2012.6152444"},{"key":"6_CR16","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-85729-479-1","volume-title":"Multimodal Interactive Pattern Recognition and Applications","author":"AH Toselli","year":"2011","unstructured":"Toselli, A.H., Vidal, E., Casacuberta, F.: Multimodal Interactive Pattern Recognition and Applications. Springer, London (2011). https:\/\/doi.org\/10.1007\/978-0-85729-479-1"},{"issue":"4","key":"6_CR17","doi-asserted-by":"publisher","first-page":"802","DOI":"10.1016\/j.csl.2011.03.001","volume":"25","author":"H Xu","year":"2011","unstructured":"Xu, H., Povey, D., Mangu, L., Zhu, J.: Minimum Bayes risk decoding and system combination based on a recursion for edit distance. Comput. Speech Lang. 25(4), 802\u2013828 (2011)","journal-title":"Comput. Speech Lang."}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition, Computer Vision, and Image Processing. ICPR 2022 International Workshops and Challenges"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-37731-0_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,9]],"date-time":"2023-08-09T14:03:06Z","timestamp":1691589786000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-37731-0_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031377303","9783031377310"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-37731-0_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"10 August 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Montr\u00e9al, QC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 August 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iapr.org\/icpr2022","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}