{"id":"https://openalex.org/W4387967920","doi":"https://doi.org/10.1145/3581783.3612272","title":"Elucidate Gender Fairness in Singing Voice Transcription","display_name":"Elucidate Gender Fairness in Singing Voice Transcription","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387967920","doi":"https://doi.org/10.1145/3581783.3612272"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612272","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612272","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612272","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612272","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042584368","display_name":"Xiangming Gu","orcid":"https://orcid.org/0000-0003-0637-8664"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiangming Gu","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-0637-8664","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100660203","display_name":"Wei Zeng","orcid":"https://orcid.org/0000-0002-0953-5314"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wei Zeng","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-0953-5314","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100423435","display_name":"Ye Wang","orcid":"https://orcid.org/0000-0002-0123-1260"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ye Wang","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-0123-1260","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.5477,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.64628334,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"8760","last_page":"8769"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9958999752998352,"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/singing","display_name":"Singing","score":0.6752959489822388},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.6700875163078308},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6062371134757996},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5748059749603271},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5313340425491333},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4348160922527313},{"id":"https://openalex.org/keywords/affect","display_name":"Affect (linguistics)","score":0.42751437425613403},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.21232739090919495},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.14388424158096313},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10050886869430542}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6752959489822388},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.6700875163078308},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6062371134757996},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5748059749603271},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5313340425491333},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4348160922527313},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.42751437425613403},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.21232739090919495},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.14388424158096313},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10050886869430542},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3581783.3612272","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612272","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612272","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/246634","is_oa":false,"landing_page_url":"https://scholarbank.nus.edu.sg/handle/10635/246634","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Elements","raw_type":"Conference Paper"}],"best_oa_location":{"id":"doi:10.1145/3581783.3612272","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612272","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612272","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Gender equality","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387967920.pdf","grobid_xml":"https://content.openalex.org/works/W4387967920.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W395933519","https://openalex.org/W1977913050","https://openalex.org/W2053363733","https://openalex.org/W2100960835","https://openalex.org/W2118774185","https://openalex.org/W2166040870","https://openalex.org/W2407685581","https://openalex.org/W2593768305","https://openalex.org/W2635912764","https://openalex.org/W2786387703","https://openalex.org/W2809878087","https://openalex.org/W2963350032","https://openalex.org/W2964159205","https://openalex.org/W2972935927","https://openalex.org/W2973071600","https://openalex.org/W3027082420","https://openalex.org/W3034700241","https://openalex.org/W3036601975","https://openalex.org/W3081279708","https://openalex.org/W3089682003","https://openalex.org/W3090751054","https://openalex.org/W3096831136","https://openalex.org/W3097489012","https://openalex.org/W3138463903","https://openalex.org/W3153182568","https://openalex.org/W3158762648","https://openalex.org/W3160649916","https://openalex.org/W3164446335","https://openalex.org/W3174602246","https://openalex.org/W3175547470","https://openalex.org/W3181414820","https://openalex.org/W3184439416","https://openalex.org/W3196906567","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3217246256","https://openalex.org/W4200633747","https://openalex.org/W4220796574","https://openalex.org/W4221159539","https://openalex.org/W4224917360","https://openalex.org/W4226106344","https://openalex.org/W4226217762","https://openalex.org/W4285192297","https://openalex.org/W4285483408","https://openalex.org/W4285819380"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2406877384","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2595839522","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W3016250102","https://openalex.org/W4288088492","https://openalex.org/W2982290989"],"abstract_inverted_index":{"It":[0],"is":[1,74],"widely":[2],"known":[3],"that":[4,83,127,161],"males":[5],"and":[6,18,51,79,110,183],"females":[7],"typically":[8],"possess":[9],"different":[10,77,84],"sound":[11],"characteristics":[12,29],"when":[13],"singing,":[14],"such":[15],"as":[16],"timbre":[17],"pitch,":[19],"but":[20],"it":[21],"has":[22],"never":[23],"been":[24],"explored":[25],"whether":[26],"these":[27],"gender-based":[28],"lead":[30],"to":[31,93,106,116,132,149,169],"a":[32,45,189],"performance":[33],"disparity":[34,46],"in":[35],"singing":[36,185],"voice":[37],"transcription":[38],"(SVT),":[39],"whose":[40],"target":[41],"includes":[42],"pitch.":[43],"Such":[44],"could":[47],"cause":[48],"fairness":[49],"issues":[50],"severely":[52],"affect":[53],"the":[54,67,113,118,124,133,150],"user":[55],"experience":[56],"of":[57,70,120,176],"downstream":[58],"SVT":[59,71,114,158,178],"applications.":[60],"Motivated":[61],"by":[62,145],"this,":[63],"we":[64,100,136],"first":[65],"demonstrate":[66],"female":[68],"superiority":[69],"systems,":[72],"which":[73],"observed":[75],"across":[76],"models":[78],"datasets.":[80],"We":[81],"find":[82],"pitch":[85,128],"distributions,":[86],"rather":[87],"than":[88,171],"gender":[89,108,134,166],"data":[90],"imbalance,":[91],"contribute":[92,131],"this":[94,98],"disparity.":[95],"To":[96],"address":[97],"issue,":[99],"propose":[101,137],"using":[102],"an":[103],"attribute":[104,151],"predictor":[105],"predict":[107],"labels":[109],"adversarially":[111],"training":[112],"system":[115],"enforce":[117],"gender-invariance":[119],"acoustic":[121,140],"representations.":[122],"Leveraging":[123],"prior":[125],"knowledge":[126],"distributions":[129],"may":[130],"bias,":[135],"conditionally":[138],"aligning":[139],"representations":[141],"between":[142],"demographic":[143],"groups":[144],"feeding":[146],"note":[147],"events":[148],"predictor.":[152],"Empirical":[153],"experiments":[154],"on":[155,180],"multiple":[156],"benchmark":[157],"datasets":[159],"show":[160],"our":[162],"method":[163],"significantly":[164],"reduces":[165],"bias":[167],"(up":[168],"more":[170],"50%)":[172],"with":[173],"negligible":[174],"degradation":[175],"overall":[177],"performance,":[179],"both":[181],"in-domain":[182],"out-of-domain":[184],"data,":[186],"thus":[187],"offering":[188],"better":[190],"fairness-utility":[191],"trade-off.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}