{"id":"https://openalex.org/W4414992123","doi":"https://doi.org/10.21437/interspeech.2025-1402","title":"Who Gets the Mic? Investigating Gender Bias in the Speaker Assignment of a Speech-LLM","display_name":"Who Gets the Mic? Investigating Gender Bias in the Speaker Assignment of a Speech-LLM","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4414992123","doi":"https://doi.org/10.21437/interspeech.2025-1402"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-1402","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1402","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.13603","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119919517","display_name":"Dariia Puhach","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dariia Puhach","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012596151","display_name":"Amir H. Payberah","orcid":"https://orcid.org/0000-0002-2748-8929"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amir H. Payberah","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5063795282","display_name":"\u00c9va Sz\u00e9kely","orcid":"https://orcid.org/0000-0003-1175-840X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"\u00c9va Sz\u00e9kely","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38612697,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2058","last_page":"2062"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.9449999928474426,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.9449999928474426,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6880000233650208},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6815000176429749},{"id":"https://openalex.org/keywords/gender-bias","display_name":"Gender bias","score":0.6319000124931335},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6118000149726868},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.43130001425743103},{"id":"https://openalex.org/keywords/selection-bias","display_name":"Selection bias","score":0.4083999991416931}],"concepts":[{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6880000233650208},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6815000176429749},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.6401000022888184},{"id":"https://openalex.org/C2983427547","wikidata":"https://www.wikidata.org/wiki/Q93200","display_name":"Gender bias","level":2,"score":0.6319000124931335},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6118000149726868},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.4406000077724457},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.43130001425743103},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.43130001425743103},{"id":"https://openalex.org/C40423286","wikidata":"https://www.wikidata.org/wiki/Q284172","display_name":"Selection bias","level":2,"score":0.4083999991416931},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.39739999175071716},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.38260000944137573},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3750999867916107},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.33070001006126404},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C2991839931","wikidata":"https://www.wikidata.org/wiki/Q48264","display_name":"Gender identity","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.26350000500679016},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.26080000400543213}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-1402","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1402","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.13603","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.13603","pdf_url":"https://arxiv.org/pdf/2508.13603","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.13603","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.13603","pdf_url":"https://arxiv.org/pdf/2508.13603","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3102226089","display_name":null,"funder_award_id":"P20-0298","funder_id":"https://openalex.org/F4320322659","funder_display_name":"Riksbankens Jubileumsfond"}],"funders":[{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"},{"id":"https://openalex.org/F4320322659","display_name":"Riksbankens Jubileumsfond","ror":"https://ror.org/02jkbm893"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414992123.pdf","grobid_xml":"https://content.openalex.org/works/W4414992123.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Similar":[0],"to":[1,19],"text-based":[2,42],"Large":[3],"Language":[4],"Models":[5],"(LLMs),":[6],"Speech-LLMs":[7,49],"exhibit":[8,120],"emergent":[9],"abilities":[10],"and":[11,109,127],"context":[12],"awareness.":[13],"However,":[14],"whether":[15],"these":[16],"similarities":[17],"extend":[18],"gender":[20,125,130],"bias":[21,39,60],"remains":[22],"an":[23,35,58],"open":[24],"question.":[25],"This":[26],"study":[27],"proposes":[28],"a":[29,52,65],"methodology":[30],"leveraging":[31],"speaker":[32,56,72,79],"assignment":[33],"as":[34],"analytic":[36],"tool":[37],"for":[38,74],"investigation.":[40],"Unlike":[41],"models,":[43],"which":[44],"encode":[45],"gendered":[46,53,84,114],"associations":[47],"implicitly,":[48],"must":[50],"produce":[51],"voice,":[54],"making":[55],"selection":[57,80],"explicit":[59],"cue.":[61],"We":[62],"evaluate":[63],"Bark,":[64],"Text-to-Speech":[66],"(TTS)":[67],"model,":[68],"analyzing":[69],"its":[70,91],"default":[71],"assignments":[73],"textual":[75],"prompts.":[76],"If":[77],"Bark's":[78],"systematically":[81],"aligns":[82],"with":[83],"associations,":[85],"it":[86,123],"may":[87],"reveal":[88],"patterns":[89],"in":[90],"training":[92],"data":[93],"or":[94],"model":[95],"design.":[96],"To":[97],"test":[98],"this,":[99],"we":[100],"construct":[101],"two":[102],"datasets:":[103],"(i)":[104],"Professions,":[105],"containing":[106],"gender-stereotyped":[107],"occupations,":[108],"(ii)":[110],"Gender-Colored":[111],"Words,":[112],"featuring":[113],"connotations.":[115],"While":[116],"Bark":[117],"does":[118],"not":[119],"systematic":[121],"bias,":[122],"demonstrates":[124],"awareness":[126],"has":[128],"some":[129],"inclinations.":[131]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-09T00:00:00"}