{"id":"https://openalex.org/W4406461890","doi":"https://doi.org/10.1109/slt61566.2024.10832259","title":"Spoken Stereoset: on Evaluating Social Bias Toward Speaker in Speech Large Language Models","display_name":"Spoken Stereoset: on Evaluating Social Bias Toward Speaker in Speech Large Language Models","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461890","doi":"https://doi.org/10.1109/slt61566.2024.10832259"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5105411292","display_name":"Yi\u2010Cheng Lin","orcid":"https://orcid.org/0009-0005-0969-631X"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yi-Cheng Lin","raw_affiliation_strings":["National Taiwan University,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100680436","display_name":"Wei-Chih Chen","orcid":"https://orcid.org/0000-0002-1127-9639"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Chih Chen","raw_affiliation_strings":["National Taiwan University,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Yi Lee","raw_affiliation_strings":["National Taiwan University,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5105411292"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":1.3571,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.85186218,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"871","last_page":"878"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9955999851226807,"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":0.9955999851226807,"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/T12031","display_name":"Speech and dialogue systems","score":0.9835000038146973,"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/T10028","display_name":"Topic Modeling","score":0.9778000116348267,"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/computer-science","display_name":"Computer science","score":0.7383397817611694},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.6280487775802612},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5937581062316895},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4160098433494568},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.41286253929138184},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3965621590614319},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34707796573638916},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.2879658639431}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7383397817611694},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.6280487775802612},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5937581062316895},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4160098433494568},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.41286253929138184},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3965621590614319},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34707796573638916},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2879658639431},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1527310062","https://openalex.org/W2074138874","https://openalex.org/W2154652894","https://openalex.org/W2154946570","https://openalex.org/W2421935140","https://openalex.org/W2498547833","https://openalex.org/W2914304175","https://openalex.org/W2954275542","https://openalex.org/W2963078909","https://openalex.org/W3096912283","https://openalex.org/W3105882417","https://openalex.org/W3147107444","https://openalex.org/W3176477796","https://openalex.org/W3206559778","https://openalex.org/W3207316473","https://openalex.org/W4220768506","https://openalex.org/W4226371168","https://openalex.org/W4296069263","https://openalex.org/W4297841287","https://openalex.org/W4323655724","https://openalex.org/W4385571232","https://openalex.org/W4386655647","https://openalex.org/W4387891768","https://openalex.org/W4388718054","https://openalex.org/W4389125242","https://openalex.org/W4391021627","https://openalex.org/W4392490008","https://openalex.org/W4395443770","https://openalex.org/W4399289687","https://openalex.org/W4402112098","https://openalex.org/W4402112459","https://openalex.org/W4402672034","https://openalex.org/W4404752324","https://openalex.org/W6682631176","https://openalex.org/W6721933647","https://openalex.org/W6791353385","https://openalex.org/W6793191273","https://openalex.org/W6856121608","https://openalex.org/W6856794988","https://openalex.org/W6856800273","https://openalex.org/W6857054612","https://openalex.org/W6859099255","https://openalex.org/W6862292725","https://openalex.org/W6864925292"],"related_works":["https://openalex.org/W2388125677","https://openalex.org/W2159057708","https://openalex.org/W405926467","https://openalex.org/W4402742086","https://openalex.org/W1965611333","https://openalex.org/W633922780","https://openalex.org/W4366957107","https://openalex.org/W2132474591","https://openalex.org/W2250825451","https://openalex.org/W2077302143"],"abstract_inverted_index":{"Warning:":[0],"This":[1,57],"paper":[2],"may":[3],"contain":[4],"texts":[5],"with":[6],"uncomfortable":[7],"content.Large":[8],"Language":[9,44],"Models":[10,45],"(LLMs)":[11],"have":[12,47],"achieved":[13],"remarkable":[14],"performance":[15,97],"in":[16,70],"various":[17],"tasks,":[18],"including":[19],"those":[20],"involving":[21],"multimodal":[22],"data":[23],"like":[24],"speech.":[25],"However,":[26],"these":[27,55,88],"models":[28,76,107],"often":[29],"exhibit":[30,113],"biases":[31,69],"due":[32],"to":[33,53,66,78,86],"the":[34,50],"nature":[35],"of":[36],"their":[37,96],"training":[38],"data.":[39],"Recently,":[40],"more":[41],"Speech":[42],"Large":[43],"(SLLMs)":[46],"emerged,":[48],"underscoring":[49],"urgent":[51],"need":[52],"address":[54],"biases.":[56,89],"study":[58],"introduces":[59],"Spoken":[60],"Stereoset,":[61],"a":[62],"dataset":[63],"specifically":[64],"designed":[65],"evaluate":[67],"social":[68],"SLLMs.":[71],"By":[72],"examining":[73],"how":[74],"different":[75],"respond":[77],"speech":[79],"from":[80],"diverse":[81],"demographic":[82],"groups,":[83],"we":[84],"aim":[85],"identify":[87],"Our":[90],"experiments":[91],"reveal":[92],"significant":[93],"insights":[94],"into":[95],"and":[98],"bias":[99],"levels.":[100],"The":[101],"findings":[102],"indicate":[103],"that":[104],"while":[105],"most":[106],"show":[108],"minimal":[109],"bias,":[110],"some":[111],"still":[112],"slightly":[114],"stereotypical":[115],"or":[116],"anti-stereotypical":[117],"tendencies.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}