{"id":"https://openalex.org/W7108704875","doi":"https://doi.org/10.5281/zenodo.17811446","title":"Sheet Music Benchmark: Standardized Optical Music Recognition Evaluation","display_name":"Sheet Music Benchmark: Standardized Optical Music Recognition Evaluation","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7108704875","doi":"https://doi.org/10.5281/zenodo.17811446"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.17811446","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811446","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.17811446","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Juan C. Martinez-Sevilla","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Juan C. Martinez-Sevilla","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Joan Cerveto-Serrano","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joan Cerveto-Serrano","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Noelia Luna-Barahona","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Noelia Luna-Barahona","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Greg Chapman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Greg Chapman","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Craig Sapp","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Craig Sapp","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":7,"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":0.62435852,"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":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9950000047683716,"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":0.9950000047683716,"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":0.0010999999940395355,"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":0.00039999998989515007,"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/notation","display_name":"Notation","score":0.7914000153541565},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6514999866485596},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5626999735832214},{"id":"https://openalex.org/keywords/musical-notation","display_name":"Musical notation","score":0.5282999873161316},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4388999938964844},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.38670000433921814},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.38109999895095825}],"concepts":[{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.7914000153541565},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6514999866485596},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6186000108718872},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5626999735832214},{"id":"https://openalex.org/C88639978","wikidata":"https://www.wikidata.org/wiki/Q233861","display_name":"Musical notation","level":3,"score":0.5282999873161316},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4388999938964844},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42410001158714294},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.38670000433921814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3840999901294708},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.38109999895095825},{"id":"https://openalex.org/C134400042","wikidata":"https://www.wikidata.org/wiki/Q2372244","display_name":"Symbol (formal)","level":2,"score":0.3580999970436096},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3452000021934509},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28519999980926514},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27950000762939453},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2777000069618225},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C143857728","wikidata":"https://www.wikidata.org/wiki/Q193544","display_name":"Music theory","level":3,"score":0.2630000114440918},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17811446","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811446","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.17811446","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811446","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":[{"score":0.4562779366970062,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,55,136],"introduce":[4,56],"the":[5,49,57,75],"Sheet":[6],"Music":[7,23],"Benchmark":[8],"(SMB),":[9],"a":[10,29,63,82,129],"dataset":[11,146],"of":[12,32],"six":[13],"hundred":[14],"and":[15,39,84,100,117,135,150],"eighty-five":[16],"pages":[17],"specifically":[18],"designed":[19],"to":[20,120],"benchmark":[21],"Optical":[22],"Recognition":[24],"(OMR)":[25],"research.":[26],"SMB":[27,145],"encompasses":[28],"diverse":[30],"array":[31],"musical":[33,91],"textures,":[34],"including":[35],"monophony,":[36],"pianoform,":[37],"quartet,":[38],"others,":[40],"all":[41],"encoded":[42],"in":[43,132],"Common":[44],"Western":[45],"Modern":[46],"Notation":[47],"using":[48,143],"Humdrum":[50],"**kern":[51],"format.":[52],"Alongside":[53],"SMB,":[54],"OMR":[58,70,123,133],"Normalized":[59],"Edit":[60],"Distance":[61],"(OMR-NED),":[62],"new":[64],"metric":[65],"tailored":[66],"explicitly":[67],"for":[68,148],"evaluating":[69],"performance.":[71],"OMR-NED":[72,111],"builds":[73],"upon":[74],"widely-used":[76],"Symbol":[77],"Error":[78],"Rate":[79],"(SER),":[80],"offering":[81],"fine-grained":[83],"detailed":[85],"error":[86],"analysis":[87],"that":[88],"covers":[89],"individual":[90],"elements":[92],"such":[93],"as":[94],"note":[95],"heads,":[96],"beams,":[97],"pitches,":[98],"accidentals,":[99],"other":[101],"critical":[102],"notation":[103],"features.":[104],"The":[105],"resulting":[106],"numeric":[107],"score":[108],"provided":[109],"by":[110],"facilitates":[112],"clear":[113],"comparisons,":[114],"enabling":[115],"researchers":[116],"end-users":[118],"alike":[119],"identify":[121],"optimal":[122],"approaches.":[124],"Our":[125],"work":[126],"thus":[127],"addresses":[128],"long-standing":[130],"gap":[131],"evaluation,":[134],"support":[137],"our":[138],"contributions":[139],"with":[140],"baseline":[141],"experiments":[142],"standardized":[144],"splits":[147],"training":[149],"assessing":[151],"state-of-the-art":[152],"methods.":[153]},"counts_by_year":[],"updated_date":"2025-12-05T23:25:22.460635","created_date":"2025-12-05T00:00:00"}