{"id":"https://openalex.org/W7141826950","doi":"https://doi.org/10.1007/s10032-026-00574-w","title":"Full-page recognition and alignment of historical musical documents","display_name":"Full-page recognition and alignment of historical musical documents","publication_year":2026,"publication_date":"2026-03-28","ids":{"openalex":"https://openalex.org/W7141826950","doi":"https://doi.org/10.1007/s10032-026-00574-w"},"language":"en","primary_location":{"id":"doi:10.1007/s10032-026-00574-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10032-026-00574-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10032-026-00574-w.pdf","source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Document Analysis and Recognition (IJDAR)","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10032-026-00574-w.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051253622","display_name":"Manuel Villarreal","orcid":"https://orcid.org/0000-0001-5490-6156"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Manuel Villarreal","raw_affiliation_strings":["Pattern Recognition and Human Language Technology Research Center, Universitat Polit\u00e9cnica de Val\u00e8ncia, Cam\u00ed de Vera, 46022, Val\u00e8ncia, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pattern Recognition and Human Language Technology Research Center, Universitat Polit\u00e9cnica de Val\u00e8ncia, Cam\u00ed de Vera, 46022, Val\u00e8ncia, Spain","institution_ids":["https://openalex.org/I60053951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130853194","display_name":"Joan Andreu S\u00e1nchez","orcid":null},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Joan Andreu S\u00e1nchez","raw_affiliation_strings":["Pattern Recognition and Human Language Technology Research Center, Universitat Polit\u00e9cnica de Val\u00e8ncia, Cam\u00ed de Vera, 46022, Val\u00e8ncia, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pattern Recognition and Human Language Technology Research Center, Universitat Polit\u00e9cnica de Val\u00e8ncia, Cam\u00ed de Vera, 46022, Val\u00e8ncia, Spain","institution_ids":["https://openalex.org/I60053951"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092255175","display_name":"Daniel Parres","orcid":"https://orcid.org/0000-0002-2078-0329"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Daniel Parres","raw_affiliation_strings":["Pattern Recognition and Human Language Technology Research Center, Universitat Polit\u00e9cnica de Val\u00e8ncia, Cam\u00ed de Vera, 46022, Val\u00e8ncia, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pattern Recognition and Human Language Technology Research Center, Universitat Polit\u00e9cnica de Val\u00e8ncia, Cam\u00ed de Vera, 46022, Val\u00e8ncia, Spain","institution_ids":["https://openalex.org/I60053951"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5051253622"],"corresponding_institution_ids":["https://openalex.org/I60053951"],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":{"value":3090,"currency":"USD","value_usd":3090},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26839299,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"29","issue":"2","first_page":"659","last_page":"674"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9598000049591064,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9598000049591064,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.016499999910593033,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.008999999612569809,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.694599986076355},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6409000158309937},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.49889999628067017},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45210000872612},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.43389999866485596},{"id":"https://openalex.org/keywords/musical-notation","display_name":"Musical notation","score":0.39430001378059387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7063000202178955},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.694599986076355},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6409000158309937},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5181999802589417},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.49889999628067017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47929999232292175},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45210000872612},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.43389999866485596},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4268999993801117},{"id":"https://openalex.org/C88639978","wikidata":"https://www.wikidata.org/wiki/Q233861","display_name":"Musical notation","level":3,"score":0.39430001378059387},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.35600000619888306},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C143857728","wikidata":"https://www.wikidata.org/wiki/Q193544","display_name":"Music theory","level":3,"score":0.2815000116825104},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.2596000134944916},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10032-026-00574-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10032-026-00574-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10032-026-00574-w.pdf","source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Document Analysis and Recognition (IJDAR)","raw_type":"journal-article"},{"id":"pmh:oai:riunet.upv.es:10251/234594","is_oa":true,"landing_page_url":"https://riunet.upv.es/handle/10251/234594","pdf_url":null,"source":{"id":"https://openalex.org/S4306400639","display_name":"RiuNet (Universitat Polit\u00e8cnica de Val\u00e8ncia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I60053951","host_organization_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","host_organization_lineage":["https://openalex.org/I60053951"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/s10032-026-00574-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10032-026-00574-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10032-026-00574-w.pdf","source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Document Analysis and Recognition (IJDAR)","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.4767247140407562,"display_name":"Sustainable cities and communities"}],"awards":[{"id":"https://openalex.org/G3480869486","display_name":null,"funder_award_id":"13039","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G6181149722","display_name":null,"funder_award_id":"CIPROM/2023/17","funder_id":"https://openalex.org/F4320321864","funder_display_name":"Generalitat Valenciana"},{"id":"https://openalex.org/G7084143925","display_name":null,"funder_award_id":"AEI/10","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320321864","display_name":"Generalitat Valenciana","ror":"https://ror.org/0097mvx21"},{"id":"https://openalex.org/F4320334905","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859"},{"id":"https://openalex.org/F4320335598","display_name":"Agencia Estatal de Investigaci\u00f3n","ror":"https://ror.org/003x0zc53"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7141826950.pdf","grobid_xml":"https://content.openalex.org/works/W7141826950.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1858214555","https://openalex.org/W2030863126","https://openalex.org/W2039708501","https://openalex.org/W2045220951","https://openalex.org/W2085884812","https://openalex.org/W2127141656","https://openalex.org/W2133817227","https://openalex.org/W2296073425","https://openalex.org/W2576552193","https://openalex.org/W2917211058","https://openalex.org/W2917340025","https://openalex.org/W2969230409","https://openalex.org/W3015315843","https://openalex.org/W3034999214","https://openalex.org/W3108895099","https://openalex.org/W3138516171","https://openalex.org/W4224434037","https://openalex.org/W4225663457","https://openalex.org/W4225723181","https://openalex.org/W4309501538","https://openalex.org/W4312233877","https://openalex.org/W4372260009","https://openalex.org/W4382202677","https://openalex.org/W4382602926","https://openalex.org/W4385595356","https://openalex.org/W4385990962","https://openalex.org/W4402343065","https://openalex.org/W4402343076","https://openalex.org/W4402423721"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Optical":[1],"Music":[2],"Recognition":[3],"aims":[4],"to":[5,78,111],"transcribe":[6],"musical":[7,29,50,71,172],"manuscript":[8],"images":[9],"into":[10],"digital":[11],"formats":[12],"by":[13],"using":[14],"automatic":[15,168],"methods":[16],"for":[17,26,67,84,99,163],"enhanced":[18],"accessibility":[19],"and":[20,38,51,72,90,94,102,158],"preservation.":[21],"This":[22,42,63,106],"task":[23],"is":[24],"challenging":[25],"handwritten":[27],"historical":[28,104,171],"pieces":[30],"from":[31,129],"the":[32,45,70,81,113,116,130,137,144,148,154,167],"Late":[33],"Middle":[34],"Ages,":[35],"Early":[36],"Renaissance,":[37],"previous":[39],"time":[40,59,82,132],"periods.":[41],"music":[43],"has":[44],"interesting":[46],"characteristic":[47],"that":[48],"both":[49],"lyrical":[52,73],"elements":[53],"are":[54,97,123],"present":[55],"with":[56],"an":[57,85],"implicit":[58],"alignment":[60,83,145,150],"between":[61],"them.":[62],"paper":[64,107],"introduces":[65],"techniques":[66,110],"simultaneously":[68],"transcribing":[69,101],"elements.":[74],"We":[75],"research":[76,165],"how":[77],"automatically":[79],"obtain":[80],"accurate":[86],"musicological":[87],"interpretation.":[88],"Convolutional":[89],"Recurrent":[91],"Neural":[92],"Networks":[93],"Transformer":[95,140],"models":[96,117,141],"explored":[98],"holistically":[100],"aligning":[103],"pieces.":[105],"explores":[108],"different":[109,127],"improve":[112],"training":[114],"of":[115,139,156,170],"in":[118,142,166],"limited":[119],"data":[120],"scenarios.":[121],"Experiments":[122],"conducted":[124],"on":[125],"two":[126],"datasets":[128],"same":[131],"period.":[133],"Our":[134],"findings":[135],"highlight":[136],"potential":[138],"overcoming":[143],"challenge,":[146],"providing":[147],"best":[149],"capabilities":[151],"without":[152],"compromising":[153],"quality":[155],"transcriptions":[157],"offering":[159],"a":[160],"promising":[161],"direction":[162],"future":[164],"recognition":[169],"documents.":[173]},"counts_by_year":[],"updated_date":"2026-08-29T07:29:34.045763","created_date":"2026-03-29T00:00:00"}
