{"id":"https://openalex.org/W4416790855","doi":"https://doi.org/10.63317/3knqp5mifai3","title":"Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation","display_name":"Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W4416790855","doi":"https://doi.org/10.63317/3knqp5mifai3"},"language":null,"primary_location":{"id":"doi:10.63317/3knqp5mifai3","is_oa":false,"landing_page_url":"https://doi.org/10.63317/3knqp5mifai3","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.21517","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045550253","display_name":"Lina Conti","orcid":"https://orcid.org/0009-0002-9312-7360"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lina Conti","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076814388","display_name":"Dennis Fucci","orcid":"https://orcid.org/0000-0002-0940-5595"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dennis Fucci","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054564363","display_name":"Marco Gaido","orcid":"https://orcid.org/0000-0003-4217-1396"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marco Gaido","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015363344","display_name":"Matteo Negri","orcid":"https://orcid.org/0000-0002-8811-4330"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matteo Negri","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013670630","display_name":"Guillaume Wisniewski","orcid":"https://orcid.org/0000-0002-4445-080X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guillaume Wisniewski","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5066183817","display_name":"Luisa Bentivogli","orcid":"https://orcid.org/0000-0001-7480-2231"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luisa Bentivogli","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":0.00912301,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2232","last_page":"2248"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.19099999964237213,"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"}},"topics":[{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.19099999964237213,"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"}},{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.10580000281333923,"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/T11640","display_name":"Linguistic Variation and Morphology","score":0.094200000166893,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"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/interpretability","display_name":"Interpretability","score":0.7425000071525574},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47679999470710754},{"id":"https://openalex.org/keywords/notional-amount","display_name":"Notional amount","score":0.3763999938964844},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.3644999861717224},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.3149999976158142},{"id":"https://openalex.org/keywords/attribution","display_name":"Attribution","score":0.3034000098705292},{"id":"https://openalex.org/keywords/grammatical-gender","display_name":"Grammatical gender","score":0.29789999127388}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7425000071525574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5870000123977661},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47679999470710754},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.43650001287460327},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4032000005245209},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.39879998564720154},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38040000200271606},{"id":"https://openalex.org/C192063788","wikidata":"https://www.wikidata.org/wiki/Q7063049","display_name":"Notional amount","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.3644999861717224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3564000129699707},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C143299363","wikidata":"https://www.wikidata.org/wiki/Q900584","display_name":"Attribution","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.30320000648498535},{"id":"https://openalex.org/C192420165","wikidata":"https://www.wikidata.org/wiki/Q162378","display_name":"Grammatical gender","level":3,"score":0.29789999127388},{"id":"https://openalex.org/C108170787","wikidata":"https://www.wikidata.org/wiki/Q3951828","display_name":"Agency (philosophy)","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.2888000011444092},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C11693617","wikidata":"https://www.wikidata.org/wiki/Q181839","display_name":"Pragmatics","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C2983427547","wikidata":"https://www.wikidata.org/wiki/Q93200","display_name":"Gender bias","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.2563000023365021}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.63317/3knqp5mifai3","is_oa":false,"landing_page_url":"https://doi.org/10.63317/3knqp5mifai3","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.21517","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2511.21517","pdf_url":"https://arxiv.org/pdf/2511.21517","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"},{"id":"doi:10.48550/arxiv.2511.21517","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.21517","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.21517","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2511.21517","pdf_url":"https://arxiv.org/pdf/2511.21517","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416790855.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Unlike":[0],"text,":[1],"speech":[2,26],"conveys":[3],"information":[4,118,191],"about":[5],"the":[6,46,52,86,142,166,187,194],"speaker,":[7,188],"such":[8,36],"as":[9,37],"gender,":[10,35,51],"through":[11,68],"acoustic":[12,117,155],"cues":[13],"like":[14],"pitch.":[15,201],"This":[16,63],"gives":[17],"rise":[18],"to":[19,45,91,94,181,186],"modality-specific":[20],"bias":[21],"concerns.":[22],"For":[23],"example,":[24],"in":[25,60,200],"translation":[27],"(ST),":[28],"when":[29],"translating":[30],"from":[31,131],"languages":[32,40],"with":[33,168],"notional":[34],"English,":[38],"into":[39],"where":[41],"gender-ambiguous":[42],"terms":[43,96,184],"referring":[44],"speaker":[47],"are":[48],"assigned":[49],"grammatical":[50],"speaker's":[53],"vocal":[54],"characteristics":[55],"may":[56],"play":[57],"a":[58,174],"role":[59],"gender":[61,93,129,170,190],"assignment.":[62],"risks":[64],"misgendering":[65],"speakers,":[66],"whether":[67],"masculine":[69,139,146],"defaults":[70],"or":[71],"vocal-based":[72],"assumptions.":[73],"Yet,":[74],"how":[75,107],"ST":[76,88],"models":[77,89,123,148],"make":[78],"these":[79,151],"decisions":[80],"remains":[81],"poorly":[82],"understood.":[83],"We":[84,120],"investigate":[85],"mechanisms":[87],"use":[90],"assign":[92],"speaker-referring":[95],"across":[97,193],"three":[98],"language":[99,112],"pairs":[100],"(en-es/fr/it).":[101],"To":[102],"do":[103,124],"so,":[104],"we":[105,163],"examine":[106],"training":[108,132],"data":[109],"patterns,":[110],"internal":[111],"model":[113,167],"(ILM)":[114],"biases,":[115],"and":[116],"interact.":[119],"find":[121],"that":[122,165],"not":[125],"simply":[126],"replicate":[127],"term-specific":[128],"associations":[130],"data,":[133],"but":[134],"learn":[135],"broader":[136],"patterns":[137],"of":[138],"prevalence.":[140],"While":[141],"ILM":[143],"exhibits":[144],"strong":[145],"bias,":[147],"can":[149],"override":[150],"preferences":[152],"based":[153],"on":[154,161,173],"input.":[156],"Using":[157],"contrastive":[158],"feature":[159],"attribution":[160],"spectrograms,":[162],"reveal":[164],"higher":[169],"accuracy":[171],"relies":[172],"previously":[175],"unknown":[176],"mechanism:":[177],"using":[178],"first-person":[179],"pronouns":[180],"link":[182],"gendered":[183],"back":[185],"accessing":[189],"distributed":[192],"frequency":[195],"spectrum":[196],"rather":[197],"than":[198],"concentrated":[199]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-28T00:00:00"}
