{"id":"https://openalex.org/W7166803493","doi":"https://doi.org/10.18653/v1/2026.acl-long.944","title":"SpeakerSleuth: Can Large Audio-Language Models Judge Speaker Consistency across Multi-turn Dialogues?","display_name":"SpeakerSleuth: Can Large Audio-Language Models Judge Speaker Consistency across Multi-turn Dialogues?","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166803493","doi":"https://doi.org/10.18653/v1/2026.acl-long.944"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.944","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.944","pdf_url":"https://aclanthology.org/2026.acl-long.944.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.944.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139810908","display_name":"Jonggeun Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jonggeun Lee","raw_affiliation_strings":["Graduate School of Data Science , Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Data Science , Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139718155","display_name":"Junseong Pyo","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Junseong Pyo","raw_affiliation_strings":["Graduate School of Data Science , Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Data Science , Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122302227","display_name":"Gyuhyeon Seo","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gyuhyeon Seo","raw_affiliation_strings":["Graduate School of Data Science , Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Data Science , Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139784812","display_name":"Yohan Jo","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yohan Jo","raw_affiliation_strings":["Graduate School of Data Science , Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Data Science , Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7929567,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20612","last_page":"20636"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.3824000060558319,"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/T12031","display_name":"Speech and dialogue systems","score":0.3824000060558319,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.29510000348091125,"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":0.041200000792741776,"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/consistency","display_name":"Consistency (knowledge bases)","score":0.4997999966144562},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.27799999713897705},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.2637999951839447},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2630000114440918},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.25360000133514404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5544000267982483},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4997999966144562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40149998664855957},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3197999894618988},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2526000142097473},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2264000028371811}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.944","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.944","pdf_url":"https://aclanthology.org/2026.acl-long.944.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.944","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.944","pdf_url":"https://aclanthology.org/2026.acl-long.944.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166803493.pdf","grobid_xml":"https://content.openalex.org/works/W7166803493.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Audio-Language":[1],"Models":[2],"(LALMs)":[3],"as":[4,8,114,120],"judges":[5],"have":[6],"emerged":[7],"a":[9,31,136,158],"prominent":[10],"approach":[11],"for":[12,135],"evaluating":[13,33],"speech":[14],"generation":[15],"quality,":[16],"yet":[17],"their":[18],"ability":[19],"to":[20,76,101,129,165,176,179],"assess":[21],"speaker":[22,39],"consistency":[23,40],"across":[24,41,55],"multi-turn":[25,42],"dialogues":[26,43],"remains":[27],"unexplored.We":[28],"present":[29],"SpeakerSleuth,":[30],"benchmark":[32],"whether":[34],"LALMs":[35],"can":[36],"reliably":[37,77],"judge":[38],"through":[44],"three":[45],"tasks":[46],"reflecting":[47],"real-world":[48],"requirements.We":[49],"construct":[50],"1,818":[51],"humanverified":[52],"evaluation":[53],"instances":[54],"four":[56],"diverse":[57],"datasets":[58],"spanning":[59],"synthetic":[60],"and":[61,147],"real":[62],"speech,":[63],"with":[64],"controlled":[65],"acoustic":[66,79,126,149,153],"difficulty.Evaluating":[67],"twelve":[68],"widely-used":[69],"LALMs,":[70],"we":[71],"find":[72],"that":[73,106,174],"models":[74,91,121,141],"struggle":[75,100],"detect":[78,130],"inconsistencies.For":[80],"instance,":[81],"given":[82],"audio":[83],"samples":[84],"of":[85],"the":[86,103,138],"same":[87],"speaker's":[88],"turns,":[89],"some":[90],"overpredict":[92],"inconsistency,":[93],"whereas":[94],"others":[95],"are":[96,107,112],"overly":[97],"lenient.Models":[98],"further":[99],"identify":[102],"exact":[104],"turns":[105,111],"problematic.When":[108],"other":[109,139],"interlocutors'":[110],"provided":[113],"textual":[115,123],"context,":[116],"performance":[117],"degrades":[118],"dramatically":[119],"prioritize":[122,166],"coherence":[124],"over":[125,168],"cues,":[127],"failing":[128],"even":[131],"obvious":[132],"gender":[133],"switches":[134],"speaker.On":[137],"hand,":[140],"perform":[142],"substantially":[143],"better":[144],"in":[145,161],"comparing":[146],"ranking":[148],"variants,":[150],"demonstrating":[151],"inherent":[152],"discrimination":[154],"capabilities.These":[155],"findings":[156],"expose":[157],"significant":[159],"bias":[160],"LALMs:":[162],"they":[163],"tend":[164],"text":[167],"acoustics,":[169],"revealing":[170],"fundamental":[171],"modality":[172],"imbalances":[173],"need":[175],"be":[177],"addressed":[178],"build":[180],"reliable":[181],"audio-language":[182],"judges.":[183]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}