{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T02:52:18Z","timestamp":1781578338635,"version":"3.54.5"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T00:00:00Z","timestamp":1777420800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T00:00:00Z","timestamp":1781568000000},"content-version":"vor","delay-in-days":48,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Discov Internet Things"],"DOI":"10.1007\/s43926-026-00332-8","type":"journal-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T13:56:00Z","timestamp":1777470960000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning-driven automatic music score recognition and digital transcription algorithm"],"prefix":"10.1007","volume":"6","author":[{"given":"Huina","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyan","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,29]]},"reference":[{"key":"332_CR1","doi-asserted-by":"publisher","first-page":"718340","DOI":"10.3389\/fcomp.2021.718340","volume":"3","author":"F Henkel","year":"2021","unstructured":"Henkel F, Widmer G. Real-time music following in score sheet images via multi-resolution prediction. Front Comput Sci. 2021;3:718340. https:\/\/doi.org\/10.3389\/fcomp.2021.718340.","journal-title":"Front Comput Sci"},{"issue":"1","key":"332_CR2","doi-asserted-by":"publisher","first-page":"14","DOI":"10.5334\/tismir.77","volume":"4","author":"D Schneider","year":"2021","unstructured":"Schneider D, Korfhage N, M\u00fchling M, L\u00fcttig P, Freisleben B. Automatic transcription of organ tablature music notation with deep neural networks. Trans Int Soc Music Inform Retr. 2021;4(1):14\u201328. https:\/\/doi.org\/10.5334\/tismir.77.","journal-title":"Trans Int Soc Music Inform Retr"},{"issue":"9","key":"332_CR3","doi-asserted-by":"publisher","first-page":"3890","DOI":"10.3390\/app11093890","volume":"11","author":"A R\u00edos-Vila","year":"2021","unstructured":"R\u00edos-Vila A, Espl\u00e0-Gomis M, Rizo D, Ponce de Leon PJ, I\u00f1esta JM. Applying automatic translation for the optical music recognition\u2019s encoding step. Appl Sci. 2021;11(9):3890. https:\/\/doi.org\/10.3390\/app11093890.","journal-title":"Appl Sci"},{"key":"332_CR4","doi-asserted-by":"publisher","first-page":"2957","DOI":"10.1109\/TASLP.2021.3110137","volume":"29","author":"F Zalkow","year":"2021","unstructured":"Zalkow F, Mueller M. CTC-based learning of chroma features for score\u2013audio music retrieval. IEEE\/ACM Trans Audio Speech Lang Process. 2021;29:2957\u201371. https:\/\/doi.org\/10.1109\/TASLP.2021.3110137.","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"issue":"1","key":"332_CR5","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1007\/s13735-021-00221-6","volume":"11","author":"C de la Fuente","year":"2022","unstructured":"de la Fuente C, Valero-Mas JJ, Castellanos FJ, Calvo-Zaragoza J. Multimodal image and audio music transcription. Int J Multimedia Inform Retr. 2022;11(1):77\u201384. https:\/\/doi.org\/10.1007\/s13735-021-00221-6.","journal-title":"Int J Multimedia Inform Retr"},{"issue":"24","key":"332_CR6","doi-asserted-by":"publisher","first-page":"3077","DOI":"10.3390\/electronics10243077","volume":"10","author":"A Lerch","year":"2021","unstructured":"Lerch A, Knees P. Machine learning applied to music\/audio signal processing. Electronics. 2021;10(24):3077. https:\/\/doi.org\/10.3390\/electronics10243077.","journal-title":"Electronics"},{"issue":"1","key":"332_CR7","doi-asserted-by":"publisher","first-page":"147","DOI":"10.12975\/rastmd.20221018","volume":"10","author":"L Borodovskaya","year":"2022","unstructured":"Borodovskaya L, Yavgildina Z, Dyganova E, Maykovskaya L, Medvedeva I. The possibilities of artificial intelligence in automatic musical transcription of the Tatar folk song. Rast M\u00fczikoloji Dergisi. 2022;10(1):147\u201361. https:\/\/doi.org\/10.12975\/rastmd.20221018.","journal-title":"Rast M\u00fczikoloji Dergisi"},{"issue":"5","key":"332_CR8","doi-asserted-by":"publisher","first-page":"146","DOI":"10.3390\/a15050146","volume":"15","author":"D Yang","year":"2022","unstructured":"Yang D, Goutam A, Ji K, Tsai TJ. Large-scale multimodal piano music identification using marketplace fingerprinting. Algorithms. 2022;15(5):146. https:\/\/doi.org\/10.3390\/a15050146.","journal-title":"Algorithms"},{"issue":"1","key":"332_CR9","doi-asserted-by":"publisher","first-page":"33","DOI":"10.3366\/ijhac.2022.0275","volume":"16","author":"O Nowitzki","year":"2022","unstructured":"Nowitzki O, Engelhardt-Nowitzki C, Fiala ML, W\u00f6ber W. Optical music recognition of printed white mensural notation: Conversion to modern notation using object detection mechanisms. Int J Humanit Comput. 2022;16(1):33\u201349. https:\/\/doi.org\/10.3366\/ijhac.2022.0275.","journal-title":"Int J HumanitComput"},{"key":"332_CR10","doi-asserted-by":"publisher","first-page":"65","DOI":"10.33398\/2523-4846-2022-18-1-65-82","volume":"18","author":"M Bolya","year":"2022","unstructured":"Bolya M. AI-supported Processing of Handwritten Transcriptions for Hungarian Folk Songs in a Digital Environment. ETHNOMUSIC. 2022;18:65\u201382. https:\/\/doi.org\/10.33398\/2523-4846-2022-18-1-65-82.","journal-title":"ETHNOMUSIC"},{"key":"332_CR11","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1016\/j.patrec.2022.04.032","volume":"158","author":"M Alfaro-Contreras","year":"2022","unstructured":"Alfaro-Contreras M, R\u00edos-Vila A, Valero-Mas JJ, I\u00f1esta JM, Calvo-Zaragoza J. Decoupling music notation to improve end-to-end Optical Music Recognition. Pattern Recognit Lett. 2022;158:157\u201363. https:\/\/doi.org\/10.1016\/j.patrec.2022.04.032.","journal-title":"Pattern Recognit Lett"},{"issue":"4","key":"332_CR12","doi-asserted-by":"publisher","first-page":"606","DOI":"10.3390\/app8040606","volume":"8","author":"J Calvo-Zaragoza","year":"2018","unstructured":"Calvo-Zaragoza J, Rizo D. End-to-end neural optical music recognition of monophonic scores. Appl Sci. 2018;8(4):606. https:\/\/doi.org\/10.3390\/app8040606.","journal-title":"Appl Sci"},{"issue":"1","key":"332_CR13","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1007\/s13735-023-00278-5","volume":"12","author":"M Alfaro-Contreras","year":"2023","unstructured":"Alfaro-Contreras M, I\u00f1esta JM, Calvo-Zaragoza J. Optical music recognition for homophonic scores with neural networks and synthetic music generation. Int J Multimedia Inform Retr. 2023;12(1):12. https:\/\/doi.org\/10.1007\/s13735-023-00278-5.","journal-title":"Int J Multimedia Inform Retr"},{"issue":"6","key":"332_CR14","doi-asserted-by":"publisher","first-page":"1853","DOI":"10.3233\/IDA-227077","volume":"27","author":"J Park","year":"2023","unstructured":"Park J, Choi K, Oh S, Kim L, Park J. Note-level singing melody transcription with transformers. Intell Data Anal. 2023;27(6):1853\u201371. https:\/\/doi.org\/10.3233\/IDA-227077.","journal-title":"Intell Data Anal"},{"issue":"16","key":"332_CR15","doi-asserted-by":"publisher","first-page":"9360","DOI":"10.3390\/app13169360","volume":"13","author":"Y Liu","year":"2023","unstructured":"Liu Y, Wu R, Wu Y, Luo L, Xu W. A Stave-Aware Optical Music Recognition on Monophonic Scores for Camera-Based Scenarios. Appl Sci. 2023;13(16):9360. https:\/\/doi.org\/10.3390\/app13169360.","journal-title":"Appl Sci"},{"key":"332_CR16","doi-asserted-by":"publisher","first-page":"6941","DOI":"10.1109\/ACCESS.2024.3350880","volume":"12","author":"P Yu","year":"2024","unstructured":"Yu P, Chen H. Deep Multilevel Cascade Residual Recurrent Framework (MCRR) for Sheet Music Recognition. IEEE Access. 2024;12:6941\u201360. https:\/\/doi.org\/10.1109\/ACCESS.2024.3350880.","journal-title":"IEEE Access"},{"issue":"7","key":"332_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3651310","volume":"20","author":"X Gu","year":"2024","unstructured":"Gu X, Ou L, Zeng W, Zhang J, Wong N, Wang Y. Automatic lyric transcription and automatic music transcription from multimodal singing. ACM Trans Multimedia Comput Commun Appl. 2024;20(7):1\u201329. https:\/\/doi.org\/10.1145\/3651310.","journal-title":"ACM Trans Multimedia Comput Commun Appl"},{"issue":"16","key":"332_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/app14167355","volume":"14","author":"A Hartelt","year":"2024","unstructured":"Hartelt A, Eipert T, Puppe F. Optical Medieval Music Recognition\u2014A Complete Pipeline for Historic Chants. Appl Sci (2076\u20133417). 2024;14(16):1\u201326. https:\/\/doi.org\/10.3390\/app14167355.","journal-title":"Appl Sci (2076\u20133417)"},{"issue":"3","key":"332_CR19","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1007\/s10032-024-00485-8","volume":"27","author":"P Torras","year":"2024","unstructured":"Torras P, Biswas S, Forn\u00e9s A. A unified representation framework for the evaluation of Optical Music Recognition systems. Int J Doc Anal Recognit (IJDAR). 2024;27(3):379\u201393. https:\/\/doi.org\/10.1007\/s10032-024-00485-8.","journal-title":"Int J Doc Anal Recognit (IJDAR)"},{"issue":"3","key":"332_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3659103","volume":"17","author":"C Wei\u00df","year":"2024","unstructured":"Wei\u00df C, M\u00fcller M. From music scores to audio recordings: Deep pitch-class representations for measuring tonal structures. ACM J Comput Cult Herit. 2024;17(3):1\u201319. https:\/\/doi.org\/10.1145\/3659103.","journal-title":"ACM J Comput Cult Herit"},{"issue":"4","key":"332_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s13735-025-00385-5","volume":"14","author":"A Rios-Vila","year":"2025","unstructured":"Rios-Vila A, Fuentes-Martinez E, Castellanos FJ. An implicit layout-aware transformer for full-page end-to-end optical music recognition. Int J Multimedia Inform Retr. 2025;14(4):1\u201314. https:\/\/doi.org\/10.1007\/s13735-025-00385-5.","journal-title":"Int J Multimedia Inform Retr"},{"key":"332_CR22","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1186\/s13636-025-00412-7","volume":"20251","author":"M Li","year":"2025","unstructured":"Li M. Design and implementation of a piano audio automatic music transcription algorithm based on a convolutional neural network. EURASIP J Audio Speech Music Process. 2025;20251:26. https:\/\/doi.org\/10.1186\/s13636-025-00412-7.","journal-title":"EURASIP J Audio Speech Music Process"},{"key":"332_CR23","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1007\/s10032-025-00541-x","volume":"28","author":"SB Oliva-Bulpitt","year":"2025","unstructured":"Oliva-Bulpitt SB, Martinez-Esteso JP, Galan-Cuenca A, Castellanos FJ, Gallego AJ. Enhancing music score analysis with Monte Carlo dropout: a probabilistic approach to staff-region detection. Int J Doc Anal Recognit (IJDAR). 2025;28:441\u201356. https:\/\/doi.org\/10.1007\/s10032-025-00541-x.","journal-title":"Int J Doc Anal Recognit (IJDAR)"},{"issue":"13","key":"332_CR24","doi-asserted-by":"publisher","first-page":"10409","DOI":"10.1007\/s00521-021-06629-9","volume":"34","author":"A Paul","year":"2022","unstructured":"Paul A, Pramanik R, Malakar S, Sarkar R. An ensemble of deep transfer learning models for handwritten music symbol recognition. Neural Comput Appl. 2022;34(13):10409\u201327. https:\/\/doi.org\/10.1007\/s00521-021-06629-9.","journal-title":"Neural Comput Appl"},{"issue":"8","key":"332_CR25","doi-asserted-by":"publisher","first-page":"3621","DOI":"10.3390\/app11083621","volume":"11","author":"M Alfaro-Contreras","year":"2021","unstructured":"Alfaro-Contreras M, Valero-Mas JJ. Exploiting the two-dimensional nature of agnostic music notation for neural optical music recognition. Appl Sci. 2021;11(8):3621. https:\/\/doi.org\/10.3390\/app11083621.","journal-title":"Appl Sci"},{"issue":"5","key":"332_CR26","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1166\/jctn.2021.9626","volume":"18","author":"M Lee","year":"2021","unstructured":"Lee M, Kim H, Moon M, Park SM. Computer-Vision-Based Advanced Optical Music Recognition System. J Comput Theor Nanosci. 2021;18(5):1345\u201351. https:\/\/doi.org\/10.1166\/jctn.2021.9626.","journal-title":"J Comput Theor Nanosci"},{"issue":"4","key":"332_CR27","doi-asserted-by":"publisher","first-page":"41","DOI":"10.4018\/IJIRR.2021100103","volume":"11","author":"S Rajesh","year":"2021","unstructured":"Rajesh S, Nalini NJ. Recognition of musical instruments using deep learning techniques. Int J Inform Retr Res (IJIRR). 2021;11(4):41\u201360. https:\/\/doi.org\/10.4018\/IJIRR.2021100103.","journal-title":"Int J Inform Retr Res (IJIRR)"},{"issue":"4","key":"332_CR28","doi-asserted-by":"publisher","first-page":"1421","DOI":"10.13053\/cys-26-4-4271","volume":"26","author":"O Velazquez Lopez","year":"2022","unstructured":"Velazquez Lopez O, Rodriguez O, J.L. and, Suarez Guerra S. Application of auditory filter-banks in polyphonic music transcription. Computaci\u00f3n y Sistemas. 2022;26(4):1421\u20138. https:\/\/doi.org\/10.13053\/cys-26-4-4271.","journal-title":"Computaci\u00f3n y Sistemas"},{"issue":"3","key":"332_CR29","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1007\/s10032-023-00432-z","volume":"26","author":"A R\u00edos-Vila","year":"2023","unstructured":"R\u00edos-Vila A, Rizo D, I\u00f1esta JM, Calvo-Zaragoza J. End-to-end optical music recognition for piano-form sheet music. Int J Doc Anal Recognit (IJDAR). 2023;26(3):347\u201362. https:\/\/doi.org\/10.1007\/s10032-023-00432-z.","journal-title":"Int J Doc Anal Recognit (IJDAR)"},{"key":"332_CR30","doi-asserted-by":"publisher","unstructured":"Mayer J, Straka M, Haji\u010d J, Pecina P. Practical end-to-end optical music recognition for piano-form music. In the International Conference on Document Analysis and Recognition. Cham: Springer Nature Switzerland, 2024;14809, pp. 55\u201373. https:\/\/doi.org\/10.1007\/978-3-031-70552-6_4.","DOI":"10.1007\/978-3-031-70552-6_4"},{"issue":"1","key":"332_CR31","doi-asserted-by":"publisher","first-page":"2540814","DOI":"10.1142\/S0129156425408149","volume":"34","author":"T Ru","year":"2025","unstructured":"Ru T. Deep Learning-Based Automatic Piano Note Recognition and Performance Generation System. Int J High Speed Electron Syst. 2025;34(1):2540814. https:\/\/doi.org\/10.1142\/S0129156425408149.","journal-title":"Int J High Speed Electron Syst"},{"issue":"1","key":"332_CR32","doi-asserted-by":"publisher","first-page":"2415857","DOI":"10.1155\/2022\/2415857","volume":"2022","author":"M Liang","year":"2022","unstructured":"Liang M. Music score recognition and composition application based on deep learning. Math Probl Eng. 2022;2022(1):2415857. https:\/\/doi.org\/10.1155\/2022\/2415857.","journal-title":"Math Probl Eng"},{"issue":"2","key":"332_CR33","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1504\/IJCSM.2025.149900","volume":"22","author":"J Wang","year":"2025","unstructured":"Wang J. Research on optical music recognition based on an improved CRNN network and its application in piano teaching. Int J Comput Sci Math. 2025;22(2):176\u201391. https:\/\/doi.org\/10.1504\/IJCSM.2025.149900.","journal-title":"Int J Comput Sci Math"}],"container-title":["Discover Internet of Things"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s43926-026-00332-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s43926-026-00332-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s43926-026-00332-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T02:08:31Z","timestamp":1781575711000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s43926-026-00332-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,29]]},"references-count":33,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["332"],"URL":"https:\/\/doi.org\/10.1007\/s43926-026-00332-8","relation":{},"ISSN":["2730-7239"],"issn-type":[{"value":"2730-7239","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,29]]},"assertion":[{"value":"16 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"78"}}