{"id":"https://openalex.org/W4391021563","doi":"https://doi.org/10.1109/asru57964.2023.10389767","title":"No Pitch Left Behind: Addressing Gender Unbalance In Automatic Speech Recognition Through Pitch Manipulation","display_name":"No Pitch Left Behind: Addressing Gender Unbalance In Automatic Speech Recognition Through Pitch Manipulation","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021563","doi":"https://doi.org/10.1109/asru57964.2023.10389767"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389767","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389767","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076814388","display_name":"Dennis Fucci","orcid":"https://orcid.org/0000-0002-0940-5595"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]},{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Dennis Fucci","raw_affiliation_strings":["Fondazione Bruno Kessler,Italy","University of Trento, Italy","Fondazione Bruno Kessler, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fondazione Bruno Kessler,Italy","institution_ids":["https://openalex.org/I2277624104"]},{"raw_affiliation_string":"University of Trento, Italy","institution_ids":["https://openalex.org/I193223587"]},{"raw_affiliation_string":"Fondazione Bruno Kessler, Italy","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054564363","display_name":"Marco Gaido","orcid":"https://orcid.org/0000-0003-4217-1396"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Gaido","raw_affiliation_strings":["Fondazione Bruno Kessler,Italy","Fondazione Bruno Kessler, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fondazione Bruno Kessler,Italy","institution_ids":["https://openalex.org/I2277624104"]},{"raw_affiliation_string":"Fondazione Bruno Kessler, Italy","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015363344","display_name":"Matteo Negri","orcid":"https://orcid.org/0000-0002-8811-4330"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Matteo Negri","raw_affiliation_strings":["Fondazione Bruno Kessler,Italy","Fondazione Bruno Kessler, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fondazione Bruno Kessler,Italy","institution_ids":["https://openalex.org/I2277624104"]},{"raw_affiliation_string":"Fondazione Bruno Kessler, Italy","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034851858","display_name":"Mauro Cettolo","orcid":null},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mauro Cettolo","raw_affiliation_strings":["Fondazione Bruno Kessler,Italy","Fondazione Bruno Kessler, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fondazione Bruno Kessler,Italy","institution_ids":["https://openalex.org/I2277624104"]},{"raw_affiliation_string":"Fondazione Bruno Kessler, Italy","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066183817","display_name":"Luisa Bentivogli","orcid":"https://orcid.org/0000-0001-7480-2231"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luisa Bentivogli","raw_affiliation_strings":["Fondazione Bruno Kessler,Italy","Fondazione Bruno Kessler, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fondazione Bruno Kessler,Italy","institution_ids":["https://openalex.org/I2277624104"]},{"raw_affiliation_string":"Fondazione Bruno Kessler, Italy","institution_ids":["https://openalex.org/I2277624104"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8158,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.79235136,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":0.9980999827384949,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9975000023841858,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.8046321868896484},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7387500405311584},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6735821962356567},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6266694068908691},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5533739924430847},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.44407007098197937},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4381582736968994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3590386211872101},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1616532802581787}],"concepts":[{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.8046321868896484},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7387500405311584},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6735821962356567},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6266694068908691},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5533739924430847},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.44407007098197937},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4381582736968994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3590386211872101},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1616532802581787},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389767","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389767","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W10987127","https://openalex.org/W222053410","https://openalex.org/W1485776204","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1571330406","https://openalex.org/W1875231349","https://openalex.org/W1922655562","https://openalex.org/W1989674786","https://openalex.org/W1995875735","https://openalex.org/W2012705052","https://openalex.org/W2041086022","https://openalex.org/W2050047474","https://openalex.org/W2099621636","https://openalex.org/W2127141656","https://openalex.org/W2137325773","https://openalex.org/W2169272853","https://openalex.org/W2183341477","https://openalex.org/W2184343439","https://openalex.org/W2407080277","https://openalex.org/W2428180336","https://openalex.org/W2607719644","https://openalex.org/W2749424389","https://openalex.org/W2789669807","https://openalex.org/W2895711189","https://openalex.org/W2922073769","https://openalex.org/W2936774411","https://openalex.org/W2962784628","https://openalex.org/W2963250244","https://openalex.org/W2972816482","https://openalex.org/W2973031805","https://openalex.org/W2983036158","https://openalex.org/W3007901261","https://openalex.org/W3015611303","https://openalex.org/W3035070478","https://openalex.org/W3083781432","https://openalex.org/W3092085609","https://openalex.org/W3095123370","https://openalex.org/W3097777922","https://openalex.org/W3112702554","https://openalex.org/W3118578889","https://openalex.org/W3147107444","https://openalex.org/W3163927590","https://openalex.org/W3186528847","https://openalex.org/W3201227339","https://openalex.org/W3211278025","https://openalex.org/W4210357269","https://openalex.org/W4210482569","https://openalex.org/W4225855594","https://openalex.org/W4287669463","https://openalex.org/W4297841705","https://openalex.org/W4385245566","https://openalex.org/W4402671955","https://openalex.org/W6608792757","https://openalex.org/W6631190155","https://openalex.org/W6639350448","https://openalex.org/W6640090968","https://openalex.org/W6675409298","https://openalex.org/W6739901393","https://openalex.org/W6784050962","https://openalex.org/W6793191273","https://openalex.org/W6851198971"],"related_works":["https://openalex.org/W1970534163","https://openalex.org/W2047138445","https://openalex.org/W2044239820","https://openalex.org/W2078307554","https://openalex.org/W24786651","https://openalex.org/W1992686877","https://openalex.org/W146937114","https://openalex.org/W1599045937","https://openalex.org/W2007734627","https://openalex.org/W1980008092"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,15,122],"recognition":[2,30],"(ASR)":[3],"systems":[4],"are":[5],"known":[6],"to":[7,10,39,133],"be":[8],"sensitive":[9],"the":[11,40,43,47,52,63,88,97,106,112,144],"sociolinguistic":[12],"variability":[13,113],"of":[14,42,54,105],"data,":[16],"in":[17,27,29,46,51,72],"which":[18],"gender":[19,64,116],"plays":[20],"a":[21,82,128],"crucial":[22],"role.":[23],"This":[24,94],"can":[25],"result":[26],"disparities":[28],"accuracy":[31],"between":[32],"male":[33],"and":[34,92,110],"female":[35,108,138],"speakers,":[36,139],"primarily":[37],"due":[38],"under-representation":[41],"latter":[44],"group":[45],"training":[48],"data.":[49],"While":[50],"context":[53],"hybrid":[55],"ASR":[56],"models":[57],"several":[58],"solutions":[59],"have":[60],"been":[61,69],"proposed,":[62],"bias":[65],"issue":[66],"has":[67],"not":[68],"explicitly":[70],"addressed":[71],"end-to-end":[73],"neural":[74],"architectures.":[75],"To":[76],"fill":[77],"this":[78],"gap,":[79],"we":[80],"propose":[81],"data":[83,98],"augmentation":[84],"technique":[85,95,126],"that":[86,124],"manipulates":[87],"fundamental":[89],"frequency":[90],"$(f0)$":[91],"formants.":[93],"reduces":[96],"unbalance":[99],"among":[100],"genders":[101],"by":[102,137],"simulating":[103],"voices":[104],"under-represented":[107],"speakers":[109],"increases":[111],"within":[114],"each":[115],"group.":[117],"Experiments":[118],"on":[119],"spontaneous":[120],"English":[121],"show":[123],"our":[125],"yields":[127],"relative":[129],"WER":[130],"improvement":[131],"up":[132],"9.87%":[134],"for":[135,143],"utterances":[136],"with":[140],"larger":[141],"gains":[142],"least-represented":[145],"$f0$":[146],"ranges.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}