{"id":"https://openalex.org/W6911922594","doi":"https://doi.org/10.5281/zenodo.14877375","title":"Unsupervised Synthetic-to-Real Adaptation for Optical Music Recognition","display_name":"Unsupervised Synthetic-to-Real Adaptation for Optical Music Recognition","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6911922594","doi":"https://doi.org/10.5281/zenodo.14877375"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877375","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877375","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.14877375","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Noelia N. Luna-Barahona","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Noelia N. Luna-Barahona","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Adri\u00e1n Rosell\u00f3","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adri\u00e1n Rosell\u00f3","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Mar\u00eda Alfaro-Contreras","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mar\u00eda Alfaro-Contreras","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"David Rizo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Rizo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Jorge Calvo-Zaragoza","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jorge Calvo-Zaragoza","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3914766,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9904999732971191,"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":0.9904999732971191,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.0027000000700354576,"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/T10860","display_name":"Speech and Audio Processing","score":0.0012000000569969416,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7448999881744385},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6237999796867371},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5479000210762024},{"id":"https://openalex.org/keywords/presentation","display_name":"Presentation (obstetrics)","score":0.46299999952316284},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.42179998755455017},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4203000068664551},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.4090999960899353},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.38089999556541443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7570000290870667},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7448999881744385},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6237999796867371},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6061999797821045},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5479000210762024},{"id":"https://openalex.org/C2777601897","wikidata":"https://www.wikidata.org/wiki/Q3409113","display_name":"Presentation (obstetrics)","level":2,"score":0.46299999952316284},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4490000009536743},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.42179998755455017},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4203000068664551},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.4090999960899353},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.400299996137619},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.3626999855041504},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2732999920845032},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2538999915122986},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877375","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877375","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":""}],"best_oa_location":{"id":"doi:10.5281/zenodo.14877375","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877375","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,49],"field":[1],"of":[2,11,91,117,132],"Optical":[3],"Music":[4],"Recognition":[5],"(OMR)":[6],"focuses":[7],"on":[8,79,163],"models":[9],"capable":[10],"reading":[12],"music":[13,97,164],"scores":[14,31,105],"from":[15,106,140],"document":[16],"images.":[17,159],"Despite":[18],"its":[19],"growing":[20],"popularity,":[21],"OMR":[22,187],"is":[23,64,173,179],"still":[24],"confined":[25],"to":[26,41,104,142,184],"settings":[27],"where":[28],"the":[29,42,47,89,124,128,133,138,149,156,171],"target":[30,134,158],"are":[32],"similar":[33],"in":[34,166],"both":[35],"musical":[36],"context":[37],"and":[38,130,175],"visual":[39,101],"presentation":[40],"data":[43,56],"used":[44],"for":[45,57,151],"training":[46,80],"model.":[48],"common":[50],"scenario,":[51],"therefore,":[52],"involves":[53],"manually":[54],"annotating":[55],"each":[58],"specific":[59],"case,":[60],"a":[61,76,81,181],"process":[62],"that":[63,120,170,176],"not":[65],"only":[66,155],"labor-intensive":[67],"but":[68],"also":[69],"raises":[70],"concerns":[71],"regarding":[72],"practicality.":[73],"We":[74],"present":[75],"methodology":[77,172],"based":[78],"neural":[82,113],"model":[83,129,139],"with":[84,189],"synthetic":[85],"images,":[86],"thus":[87],"reducing":[88],"difficulty":[90],"obtaining":[92],"labeled":[93],"data.":[94],"As":[95],"sheet":[96],"renderings":[98],"depict":[99],"regular":[100],"characteristics":[102],"compared":[103],"real":[107],"collections,":[108],"we":[109],"propose":[110],"an":[111],"unsupervised":[112,146],"adaptation":[114,147,178],"approach":[115],"consisting":[116],"loss":[118],"functions":[119],"promote":[121],"alignment":[122],"between":[123],"features":[125],"learned":[126],"by":[127],"those":[131],"collection":[135],"while":[136],"preventing":[137],"converging":[141],"undesirable":[143],"solutions.":[144],"This":[145],"bypasses":[148],"need":[150],"extensive":[152],"retraining,":[153],"requiring":[154],"unlabeled":[157],"Our":[160],"experiments,":[161],"focused":[162],"written":[165],"Mensural":[167],"notation,":[168],"demonstrate":[169],"successful":[174],"synthetic-to-real":[177],"indeed":[180],"promising":[182],"way":[183],"create":[185],"practical":[186],"systems":[188],"little":[190],"human":[191],"effort.":[192]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}