{"id":"https://openalex.org/W7204244498","doi":"https://doi.org/10.18653/2026.salma-1.6","title":"Lost in Speech: Trilingual Spoken Hallucination Detection Across Audio and Transcripts","display_name":"Lost in Speech: Trilingual Spoken Hallucination Detection Across Audio and Transcripts","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7204244498","doi":"https://doi.org/10.18653/2026.salma-1.6"},"language":"en","primary_location":{"id":"doi:10.18653/2026.salma-1.6","doi":"https://doi.org/10.18653/2026.salma-1.6","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.salma-1.6","pdf_url":"https://aclanthology.org/2026.salma-1.6.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Proceedings of Speech and Audio Language Models Workshop (2nd Edition)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.salma-1.6.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120145076","display_name":"Meruyert Aristombayeva","orcid":"https://orcid.org/0000-0002-2609-5867","observed_orcids":["https://orcid.org/0000-0002-2609-5867"]},"institutions":[{"id":"https://openalex.org/I204275683","display_name":"Satbayev University","ror":"https://ror.org/020cpsb96","country_code":"KZ","type":"education","lineage":["https://openalex.org/I204275683"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Meruyert Aristombayeva","raw_affiliation_strings":["Satbayev University , Almaty , Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Satbayev University , Almaty , Kazakhstan","institution_ids":["https://openalex.org/I204275683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127938019","display_name":"Jason S Lucas","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason S Lucas","raw_affiliation_strings":["University of Colorado Boulder , Boulder , CO , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Colorado Boulder , Boulder , CO , USA","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125743354","display_name":"Chaewan Chun","orcid":"https://orcid.org/0009-0006-3627-7222","observed_orcids":["https://orcid.org/0009-0006-3627-7222"]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chaewan Chun","raw_affiliation_strings":["The Pennsylvania State University , University Park , PA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University , University Park , PA , USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100405086","display_name":"Dongwon Lee","orcid":"https://orcid.org/0000-0001-8371-7629","observed_orcids":["https://orcid.org/0000-0001-8371-7629"]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongwon Lee","raw_affiliation_strings":["The Pennsylvania State University , University Park , PA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University , University Park , PA , USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.63602147,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"53","last_page":"73"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"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/T11147","display_name":"Misinformation and Its Impacts","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.0012000000569969416,"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":0.0010999999940395355,"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/asr-transcripts","display_name":"ASR transcripts","score":0.8999999761581421},{"id":"https://openalex.org/keywords/misinformation","display_name":"misinformation","score":0.3709999918937683},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.7590000033378601},{"id":"https://openalex.org/keywords/russian","display_name":"Russian","score":0.6930000185966492},{"id":"https://openalex.org/keywords/kazakhs","display_name":"Kazakhs","score":1.0},{"id":"https://openalex.org/keywords/english-language","display_name":"English language","score":0.7329999804496765},{"id":"https://openalex.org/keywords/multilingual-encoders","display_name":"multilingual encoders","score":0.5479999780654907},{"id":"https://openalex.org/keywords/provenance-analysis","display_name":"provenance analysis","score":0.6019999980926514}],"concepts":[{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.6161999702453613},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5893999934196472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5192000269889832},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5041999816894531},{"id":"https://openalex.org/C2781297163","wikidata":"https://www.wikidata.org/wiki/Q9252","display_name":"Kazakh","level":2,"score":0.49619999527931213},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4690999984741211},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4000000059604645},{"id":"https://openalex.org/C2776706361","wikidata":"https://www.wikidata.org/wiki/Q1054088","display_name":"Auditory hallucination","level":3,"score":0.3959999978542328},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.38190001249313354},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3799999952316284},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3718000054359436},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.36340001225471497},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.28299999237060547},{"id":"https://openalex.org/C2987487971","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexical access","level":3,"score":0.2702000141143799},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.257099986076355}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.salma-1.6","doi":"https://doi.org/10.18653/2026.salma-1.6","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.salma-1.6","pdf_url":"https://aclanthology.org/2026.salma-1.6.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Proceedings of Speech and Audio Language Models Workshop (2nd Edition)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2608.24707","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24707","pdf_url":"https://arxiv.org/pdf/2608.24707","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,"listed_in":[],"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.2608.24707","doi":"https://doi.org/10.48550/arxiv.2608.24707","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.24707","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,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/2026.salma-1.6","doi":"https://doi.org/10.18653/2026.salma-1.6","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.salma-1.6","pdf_url":"https://aclanthology.org/2026.salma-1.6.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Proceedings of Speech and Audio Language Models Workshop (2nd Edition)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310419","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204244498.pdf","grobid_xml":"https://content.openalex.org/works/W7204244498.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7165662907","https://openalex.org/W7155452512","https://openalex.org/W4415334968","https://openalex.org/W7106257367","https://openalex.org/W4412944702","https://openalex.org/W4414972588","https://openalex.org/W7162402683","https://openalex.org/W7214767563","https://openalex.org/W4415160220","https://openalex.org/W7166796202"],"abstract_inverted_index":{"While":[0],"text-based":[1],"hallucination":[2,180],"detection":[3,8],"is":[4],"well":[5],"studied,":[6],"reference-free":[7,101],"of":[9],"factual":[10],"alterations":[11],"in":[12,57,130,152,178],"speech":[13],"remains":[14],"underexplored,":[15],"especially":[16],"for":[17],"low-resource":[18],"languages.Our":[19],"spoken":[20],"benchmark":[21],"comprises":[22],"12,013":[23],"English,":[24],"Russian,":[25],"and":[26,35,48,60,68,79,86,146,155,171],"Kazakh":[27,61],"news":[28],"samples":[29],"with":[30,42],"three":[31,36],"synthetic":[32,179],"alteration":[33],"types":[34],"severity":[37],"levels,":[38],"pairing":[39],"source":[40,93,109,164],"articles":[41,94],"rewrites":[43],"as":[44],"text,":[45,84],"synthesized":[46],"audio,":[47],"ASR":[49,116],"transcripts.We":[50],"add":[51],"290":[52],"fact-checked":[53],"misinformation":[54,163],"items":[55],"collected":[56],"Russian":[58,166],"(225)":[59],"(65),":[62],"translated":[63],"into":[64],"the":[65,71,98,119,126,135],"other":[66,136],"language":[67],"rendered":[69],"through":[70],"same":[72],"TTS-ASR":[73],"pipeline.We":[74],"evaluate":[75],"finetuned":[76],"multilingual":[77],"encoders":[78],"zero-shot":[80],"multimodal":[81],"decoders":[82],"on":[83,118,132,161],"transcripts,":[85],"audio.Detectors":[87],"receive":[88],"only":[89,123],"target":[90],"inputs":[91],"without":[92],"or":[95],"external":[96],"evidence;":[97],"task":[99],"evaluates":[100],"classification":[102],"rather":[103],"than":[104],"evidence-grounded":[105],"verification.Encoder":[106],"degradation":[107],"from":[108],"text":[110],"to":[111],"transcripts":[112,133,147],"generally":[113],"tracks":[114],"per-language":[115],"error":[117],"binary":[120,127],"task.Among":[121],"decoders,":[122],"Gemma-3n":[124],"exceeds":[125],"majority-class":[128],"baseline":[129],"macro-F1,":[131],"only;":[134],"four":[137],"do":[138],"not":[139],"exceed":[140],"their":[141],"respective":[142],"baselines.Comparisons":[143],"between":[144],"audio":[145],"are":[148],"confounded":[149],"by":[150],"differences":[151],"evaluation":[153],"coverage":[154],"class":[156],"balance.Synthetic-trained":[157],"detectors":[158],"achieve":[159],"0.82-0.88macro-F1":[160],"real-world":[162],"text;":[165],"provenance":[167],"analysis":[168],"reveals":[169],"veracity-related":[170],"modeldependent":[172],"machine-style":[173],"signals,":[174],"a":[175],"key":[176],"confound":[177],"benchmarks.":[181]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2026-08-27T00:00:00"}
