{"id":"https://openalex.org/W4416034265","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1044","title":"Fairness in Automatic Speech Recognition Isn\u2019t a One-Size-Fits-All","display_name":"Fairness in Automatic Speech Recognition Isn\u2019t a One-Size-Fits-All","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034265","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1044"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1044","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1044","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1044.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1044.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093836330","display_name":"Hend ElGhazaly","orcid":null},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hend ElGhazaly","raw_affiliation_strings":["School of Computer Science , The University of Sheffield United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , The University of Sheffield United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047085856","display_name":"Bahman Mirheidari","orcid":"https://orcid.org/0000-0002-7797-2778"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bahman Mirheidari","raw_affiliation_strings":["School of Computer Science , The University of Sheffield United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , The University of Sheffield United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045619924","display_name":"Heidi Christensen","orcid":"https://orcid.org/0000-0003-3028-5062"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Heidi Christensen","raw_affiliation_strings":["School of Computer Science , The University of Sheffield United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , The University of Sheffield United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054918343","display_name":"Nafise Sadat Moosavi","orcid":"https://orcid.org/0000-0002-8332-307X"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nafise Sadat Moosavi","raw_affiliation_strings":["School of Computer Science , The University of Sheffield United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , The University of Sheffield United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29795403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19169","last_page":"19178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.3271999955177307,"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":0.3271999955177307,"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":0.0843999981880188,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.044599998742341995,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.357699990272522},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.30410000681877136},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2824999988079071},{"id":"https://openalex.org/keywords/automatic-target-recognition","display_name":"Automatic target recognition","score":0.28139999508857727},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.2705000042915344},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.26350000500679016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6244999766349792},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5954999923706055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41269999742507935},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.357699990272522},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.30410000681877136},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.302700012922287},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C117623542","wikidata":"https://www.wikidata.org/wiki/Q621974","display_name":"Automatic target recognition","level":3,"score":0.28139999508857727},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2705000042915344},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.2517000138759613},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1044","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1044","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1044.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1044","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1044","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1044.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034265.pdf","grobid_xml":"https://content.openalex.org/works/W4416034265.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modern":[0],"Automatic":[1],"Speech":[2],"Recognition":[3],"(ASR)":[4],"systems":[5],"are":[6,48],"increasingly":[7],"deployed":[8],"in":[9,73],"highstakes":[10],"settings,":[11],"including":[12],"clinical":[13],"interviews,":[14],"public":[15],"services,":[16],"and":[17,63,97,114,118,126,175],"educational":[18],"tools,":[19],"where":[20],"equitable":[21],"performance":[22,42,108],"across":[23,45,109],"speaker":[24],"groups":[25],"is":[26],"essential.While":[27],"pre-trained":[28],"speech":[29],"models":[30],"like":[31],"Whisper":[32,81],"achieve":[33],"strong":[34],"overall":[35],"accuracy,":[36],"they":[37],"often":[38],"exhibit":[39],"inconsistent":[40],"grouplevel":[41],"that":[43,103,130,142],"varies":[44],"domains.These":[46],"disparities":[47],"not":[49,146],"fixed":[50],"properties":[51],"of":[52,112],"the":[53,58,84,131,134,171],"model,":[54,61],"but":[55],"emerge":[56],"from":[57],"interaction":[59],"between":[60],"data,":[62],"task-posing":[64],"challenges":[65],"for":[66],"fairness":[67,72,113,137,143,165],"interventions":[68],"designed":[69],"indomain.We":[70],"frame":[71],"ASR":[74],"as":[75],"a":[76,80,98,158],"generalisation":[77],"problem.We":[78],"fine-tune":[79],"model":[82],"on":[83,119],"Fair-Speech":[85],"corpus":[86],"using":[87],"four":[88],"strategies:":[89],"basic":[90],"fine-tuning,":[91],"demographic":[92],"rebalancing,":[93],"gender-swapped":[94],"data":[95,173],"augmentation,":[96],"novel":[99],"contrastive":[100,155],"learning":[101],"objective":[102],"encourages":[104],"gender-invariant":[105],"representations.We":[106],"evaluate":[107],"multiple":[110],"aspects":[111],"utility,":[115],"both":[116],"in-domain":[117,136],"three":[120],"out-of-domain":[121],"test":[122],"sets:":[123],"LibriSpeech,":[124],"EdAcc,":[125],"CognoSpeak.Our":[127],"findings":[128],"show":[129],"method":[132,156],"with":[133,176],"best":[135],"performed":[138],"worst":[139],"out-of-domain,":[140],"illustrating":[141],"gains":[144],"do":[145],"always":[147],"generalise.Demographic":[148],"balancing":[149],"generalises":[150],"more":[151],"consistently,":[152],"while":[153],"our":[154],"offers":[157],"practical":[159],"alternative:":[160],"it":[161],"achieves":[162],"stable,":[163],"crossdomain":[164],"improvements":[166],"without":[167],"requiring":[168],"changes":[169],"to":[170],"training":[172],"distribution,":[174],"minimal":[177],"accuracy":[178],"trade-offs.":[179]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}