{"id":"https://openalex.org/W4395031692","doi":"https://doi.org/10.1145/3659103","title":"From Music Scores to Audio Recordings: Deep Pitch-Class Representations for Measuring Tonal Structures","display_name":"From Music Scores to Audio Recordings: Deep Pitch-Class Representations for Measuring Tonal Structures","publication_year":2024,"publication_date":"2024-04-23","ids":{"openalex":"https://openalex.org/W4395031692","doi":"https://doi.org/10.1145/3659103"},"language":"en","primary_location":{"id":"doi:10.1145/3659103","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3659103","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3659103","source":{"id":"https://openalex.org/S4210184050","display_name":"Journal on Computing and Cultural Heritage","issn_l":"1556-4673","issn":["1556-4673","1556-4711"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal on Computing and Cultural Heritage","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3659103","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035848608","display_name":"Ch. Wei\u00df","orcid":"https://orcid.org/0000-0003-2143-4679"},"institutions":[{"id":"https://openalex.org/I25974101","display_name":"University of W\u00fcrzburg","ror":"https://ror.org/00fbnyb24","country_code":"DE","type":"education","lineage":["https://openalex.org/I25974101"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christof Wei\u00df","raw_affiliation_strings":["Center for Artificial Intelligence and Data Science, Universit\u00e4t W\u00fcrzburg, W\u00fcrzburg, Germany"],"raw_orcid":"https://orcid.org/0000-0003-2143-4679","affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence and Data Science, Universit\u00e4t W\u00fcrzburg, W\u00fcrzburg, Germany","institution_ids":["https://openalex.org/I25974101"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109881851","display_name":"Meinard M\u00fcller","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Meinard M\u00fcller","raw_affiliation_strings":["International Audio Laboratories Erlangen, Erlangen, Germany"],"raw_orcid":"https://orcid.org/0000-0001-6062-7524","affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen, Erlangen, Germany","institution_ids":["https://openalex.org/I4210123192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1262,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75462297,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"17","issue":"3","first_page":"1","last_page":"19"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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":0.9988999962806702,"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/class","display_name":"Class (philosophy)","score":0.6175382733345032},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5138252377510071},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3790418803691864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24088236689567566}],"concepts":[{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6175382733345032},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5138252377510071},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3790418803691864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24088236689567566}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3659103","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3659103","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3659103","source":{"id":"https://openalex.org/S4210184050","display_name":"Journal on Computing and Cultural Heritage","issn_l":"1556-4673","issn":["1556-4673","1556-4711"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal on Computing and Cultural Heritage","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3659103","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3659103","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3659103","source":{"id":"https://openalex.org/S4210184050","display_name":"Journal on Computing and Cultural Heritage","issn_l":"1556-4673","issn":["1556-4673","1556-4711"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal on Computing and Cultural Heritage","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4395031692.pdf"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1561949603","https://openalex.org/W1979654135","https://openalex.org/W1980497326","https://openalex.org/W1989216934","https://openalex.org/W2054623822","https://openalex.org/W2066903463","https://openalex.org/W2083181815","https://openalex.org/W2148899569","https://openalex.org/W2170142018","https://openalex.org/W2194775991","https://openalex.org/W2560254426","https://openalex.org/W2561675875","https://openalex.org/W2565932543","https://openalex.org/W2759171953","https://openalex.org/W2771265026","https://openalex.org/W2773294482","https://openalex.org/W2774379872","https://openalex.org/W2900365452","https://openalex.org/W2900370390","https://openalex.org/W2906214917","https://openalex.org/W2946729882","https://openalex.org/W3006654639","https://openalex.org/W3092503242","https://openalex.org/W3096508889","https://openalex.org/W3101246092","https://openalex.org/W3101943858","https://openalex.org/W3137158725","https://openalex.org/W3146005604","https://openalex.org/W3162528130","https://openalex.org/W3186528344","https://openalex.org/W3197905771","https://openalex.org/W4292826157","https://openalex.org/W4387943290"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0],"availability":[1],"of":[2,24,82,89,127,142,206],"digital":[3],"music":[4,13,16,55,154],"data":[5,215],"in":[6,98,219],"various":[7],"modalities":[8],"provides":[9],"opportunities":[10],"both":[11],"for":[12,46,216],"enjoyment":[14],"and":[15,49,79,157,203,226],"research.":[17],"Regarding":[18],"the":[19,21,75,87,106,128,140,174,177,220],"latter,":[20],"computer-assisted":[22],"analysis":[23],"tonal":[25,83,144,207],"structures":[26,84,145],"is":[27,229],"a":[28,119,147,198],"central":[29],"topic.":[30],"For":[31],"Western":[32],"classical":[33],"music,":[34],"studies":[35],"typically":[36],"rely":[37],"on":[38,134,153,182],"machine-readable":[39],"scores,":[40],"which":[41,58,102],"are":[42,59,95],"tedious":[43],"to":[44,73,176,197,212],"create":[45],"large-scale":[47,185],"works":[48],"comprehensive":[50],"corpora.":[51],"As":[52],"an":[53,99,224],"alternative,":[54],"audio":[56,129],"recordings,":[57],"readily":[60],"available,":[61],"can":[62],"be":[63],"analyzed":[64],"with":[65,169],"computational":[66,221],"methods.":[67],"With":[68],"this":[69],"article,":[70],"we":[71,117,123,138,165],"want":[72],"bridge":[74],"gap":[76],"between":[77,201],"score-":[78,202],"audio-based":[80,204],"measurements":[81,168,205],"by":[85],"leveraging":[86],"power":[88],"deep":[90,193],"neural":[91],"networks.":[92],"Such":[93],"networks":[94,132],"commonly":[96],"trained":[97,133],"end-to-end":[100],"fashion,":[101],"introduces":[103],"biases":[104],"towards":[105,110],"training":[107,162],"repertoire":[108],"or":[109],"specific":[111,143],"annotators.":[112],"To":[113],"overcome":[114],"these":[115,167],"problems,":[116],"propose":[118],"multi-step":[120],"strategy.":[121],"First,":[122],"compute":[124],"pitch-class":[125,194],"representations":[126,195],"recordings":[130],"using":[131,146],"score\u2013audio":[135],"pairs.":[136],"Second,":[137],"measure":[139],"presence":[141],"pattern-matching":[148],"technique":[149],"that":[150,192],"solely":[151],"relies":[152],"theory":[155],"knowledge":[156],"does":[158],"not":[159],"require":[160],"annotated":[161],"data.":[163],"Third,":[164],"highlight":[166],"interactive":[170],"visualizations,":[171],"thus":[172,209],"leaving":[173],"interpretation":[175],"musicological":[178],"experts.":[179],"Our":[180],"experiments":[181],"Richard":[183],"Wagner's":[184],"cycle":[186],"Der":[187],"Ring":[188],"des":[189],"Nibelungen":[190],"indicate":[191],"lead":[196],"high":[199],"similarity":[200],"structures,":[208],"demonstrating":[210],"how":[211],"leverage":[213],"multi-modal":[214],"application":[217],"scenarios":[218],"humanities,":[222],"where":[223],"explicit":[225],"interpretable":[227],"methodology":[228],"essential.":[230]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}