{"id":"https://openalex.org/W7108696322","doi":"https://doi.org/10.5281/zenodo.17811464","title":"Optical Music Recognition of Jazz Lead Sheets","display_name":"Optical Music Recognition of Jazz Lead Sheets","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7108696322","doi":"https://doi.org/10.5281/zenodo.17811464"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.17811464","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811464","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.17811464","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Juan Carlos Martinez-Sevilla","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Juan Carlos Martinez-Sevilla","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Francesco Foscarin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Francesco Foscarin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Patricia Garcia-Iasci","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patricia Garcia-Iasci","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":"middle","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":[]},{"author_position":"last","author":{"id":null,"display_name":"Gerhard Widmer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gerhard Widmer","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"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":0.63072843,"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":0.9805999994277954,"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":0.9805999994277954,"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":0.008299999870359898,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.0020000000949949026,"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/jazz","display_name":"Jazz","score":0.8526999950408936},{"id":"https://openalex.org/keywords/lead","display_name":"Lead (geology)","score":0.5870000123977661},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5530999898910522},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5220000147819519},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.4442000091075897},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.41190001368522644}],"concepts":[{"id":"https://openalex.org/C2980749","wikidata":"https://www.wikidata.org/wiki/Q8341","display_name":"Jazz","level":2,"score":0.8526999950408936},{"id":"https://openalex.org/C2777093003","wikidata":"https://www.wikidata.org/wiki/Q6508345","display_name":"Lead (geology)","level":2,"score":0.5870000123977661},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5530999898910522},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5220000147819519},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4909999966621399},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47760000824928284},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.4442000091075897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.438400000333786},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41190001368522644},{"id":"https://openalex.org/C2777877512","wikidata":"https://www.wikidata.org/wiki/Q1116097","display_name":"Common ground","level":2,"score":0.40380001068115234},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.3596999943256378},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35370001196861267},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.31220000982284546},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3102000057697296},{"id":"https://openalex.org/C2781468064","wikidata":"https://www.wikidata.org/wiki/Q1267117","display_name":"Lead time","level":2,"score":0.2992999851703644}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17811464","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811464","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.17811464","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811464","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":{"In":[0],"this":[1],"paper,":[2],"we":[3],"address":[4],"the":[5,34,48,100,107,129],"challenge":[6],"of":[7,36,68,74,109,126,131],"Optical":[8],"Music":[9],"Recognition":[10],"(OMR)":[11],"for":[12,113],"handwritten":[13,56,70],"jazz":[14,71,114],"lead":[15,72,115],"sheets,":[16],"a":[17,38,64],"widely":[18],"used":[19],"musical":[20],"score":[21,39],"type":[22],"that":[23],"encodes":[24],"melody":[25],"and":[26,47,51,87,128,135,144],"chords.":[27],"The":[28,103],"task":[29],"is":[30,60,106],"challenging":[31],"due":[32],"to":[33,79,123],"presence":[35],"chords,":[37],"component":[40],"not":[41],"handled":[42],"by":[43],"existing":[44],"OMR":[45,111],"systems,":[46],"high":[49],"variability":[50],"quality":[52],"issues":[53],"associated":[54],"with":[55,84],"images.":[57],"Our":[58],"contribution":[59,105],"two-fold.":[61],"We":[62,92,117,138],"present":[63],"novel":[65],"dataset":[66],"consisting":[67],"293":[69],"sheets":[73],"163":[75],"unique":[76],"pieces,":[77],"amounting":[78],"2021":[80],"total":[81],"staves":[82],"aligned":[83],"Humdrum":[85],"**kern":[86],"MusicXML":[88],"ground":[89,101],"truth":[90],"scores.":[91],"also":[93],"supply":[94],"synthetic":[95,133],"scores":[96,134],"images":[97],"generated":[98],"from":[99],"truth.":[102],"second":[104],"development":[108],"an":[110],"model":[112],"sheets.":[116],"discuss":[118],"specific":[119],"tokenisation":[120],"choices":[121],"related":[122],"our":[124],"kind":[125],"data,":[127,143],"advantages":[130],"using":[132],"pretrained":[136],"models.":[137,145],"publicly":[139],"release":[140],"all":[141],"code,":[142]},"counts_by_year":[],"updated_date":"2025-12-05T23:25:22.460635","created_date":"2025-12-05T00:00:00"}
