{"id":"https://openalex.org/W4391833135","doi":"https://doi.org/10.1145/3630106.3658996","title":"Careless Whisper: Speech-to-Text Hallucination Harms","display_name":"Careless Whisper: Speech-to-Text Hallucination Harms","publication_year":2024,"publication_date":"2024-06-03","ids":{"openalex":"https://openalex.org/W4391833135","doi":"https://doi.org/10.1145/3630106.3658996"},"language":"en","primary_location":{"id":"doi:10.1145/3630106.3658996","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630106.3658996","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630106.3658996","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2024 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3630106.3658996","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087471530","display_name":"Allison Koenecke","orcid":"https://orcid.org/0000-0002-6233-8256"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Allison Koenecke","raw_affiliation_strings":["Cornell University, USA"],"raw_orcid":"https://orcid.org/0000-0002-6233-8256","affiliations":[{"raw_affiliation_string":"Cornell University, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102733770","display_name":"Anna Seo Gyeong Choi","orcid":"https://orcid.org/0009-0006-2482-2713"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anna Seo Gyeong Choi","raw_affiliation_strings":["Cornell University, USA"],"raw_orcid":"https://orcid.org/0009-0006-2482-2713","affiliations":[{"raw_affiliation_string":"Cornell University, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046575052","display_name":"K. Mei","orcid":"https://orcid.org/0009-0004-9685-3936"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katelyn X. Mei","raw_affiliation_strings":["University of Washington, USA"],"raw_orcid":"https://orcid.org/0009-0004-9685-3936","affiliations":[{"raw_affiliation_string":"University of Washington, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006651432","display_name":"Hilke Schellmann","orcid":"https://orcid.org/0009-0008-0233-6970"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hilke Schellmann","raw_affiliation_strings":["New York University, USA"],"raw_orcid":"https://orcid.org/0009-0008-0233-6970","affiliations":[{"raw_affiliation_string":"New York University, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075302056","display_name":"Mona Sloane","orcid":"https://orcid.org/0000-0003-1049-2267"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mona Sloane","raw_affiliation_strings":["University of Virginia, USA"],"raw_orcid":"https://orcid.org/0000-0003-1049-2267","affiliations":[{"raw_affiliation_string":"University of Virginia, USA","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":258.1033,"has_fulltext":true,"cited_by_count":71,"citation_normalized_percentile":{"value":0.99998458,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1672","last_page":"1681"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13877","display_name":"Law in Society and Culture","score":0.9185000061988831,"subfield":{"id":"https://openalex.org/subfields/3308","display_name":"Law"},"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/T13877","display_name":"Law in Society and Culture","score":0.9185000061988831,"subfield":{"id":"https://openalex.org/subfields/3308","display_name":"Law"},"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/indirect-speech","display_name":"Indirect speech","score":0.5528042316436768},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.466136634349823},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.4456864595413208},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4007679224014282},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3895501494407654},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3562633991241455},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.06999233365058899}],"concepts":[{"id":"https://openalex.org/C163765913","wikidata":"https://www.wikidata.org/wiki/Q1006348","display_name":"Indirect speech","level":2,"score":0.5528042316436768},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.466136634349823},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4456864595413208},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4007679224014282},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3895501494407654},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3562633991241455},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06999233365058899}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3630106.3658996","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630106.3658996","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630106.3658996","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2024 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2402.08021","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.08021","pdf_url":"https://arxiv.org/pdf/2402.08021","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3630106.3658996","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630106.3658996","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630106.3658996","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2024 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3217867368","display_name":null,"funder_award_id":"DC008524","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"},{"id":"https://openalex.org/G6525791409","display_name":null,"funder_award_id":"R01-DC008524","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337352","display_name":"National Institute on Deafness and Other Communication Disorders","ror":"https://ror.org/04mhx6838"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391833135.pdf"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W604972776","https://openalex.org/W1999318234","https://openalex.org/W2052167642","https://openalex.org/W2080213370","https://openalex.org/W2276983060","https://openalex.org/W2508777706","https://openalex.org/W2796439139","https://openalex.org/W2889294685","https://openalex.org/W2909600415","https://openalex.org/W3012624518","https://openalex.org/W3157070662","https://openalex.org/W4226031872","https://openalex.org/W4251388527","https://openalex.org/W4309674289","https://openalex.org/W4317830346","https://openalex.org/W4322761615","https://openalex.org/W4375959287","https://openalex.org/W4388248375","https://openalex.org/W4391224760","https://openalex.org/W6818723395"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2295571408","https://openalex.org/W2081310238","https://openalex.org/W2576539512","https://openalex.org/W2931662336","https://openalex.org/W2077865380","https://openalex.org/W2134894512","https://openalex.org/W2053487507","https://openalex.org/W2765597752","https://openalex.org/W2083375246"],"abstract_inverted_index":{"Speech-to-text":[0],"services":[1],"aim":[2],"to":[3,127,163,171],"transcribe":[4],"input":[5],"audio":[6,60],"as":[7,9,43,94],"accurately":[8],"possible.":[10],"They":[11],"increasingly":[12],"play":[13],"a":[14,34,124,135],"role":[15],"in":[16,21,26,72,75,115,168,180],"everyday":[17],"life,":[18],"for":[19,144],"example":[20],"personal":[22],"voice":[23],"assistants":[24],"or":[25,66,101],"customer-company":[27],"interactions.":[28],"We":[29,79,105,138,158],"evaluate":[30],"Open":[31],"AI\u2019s":[32],"Whisper,":[33,169],"state-of-the-art":[35],"automated":[36],"speech":[37,131],"recognition":[38],"service":[39],"outperforming":[40],"industry":[41,161],"competitors,":[42],"of":[44,48,59,88,151,156,174,183],"2023.":[45],"While":[46],"many":[47],"Whisper\u2019s":[49],"transcriptions":[50,61],"were":[51],"highly":[52],"accurate,":[53],"we":[54],"find":[55,139],"that":[56,86,140],"roughly":[57],"1%":[58],"contained":[62],"entire":[63],"hallucinated":[64],"phrases":[65],"sentences":[67],"which":[68],"did":[69],"not":[70],"exist":[71],"any":[73],"form":[74],"the":[76,82,113],"underlying":[77],"audio.":[78],"thematically":[80],"analyze":[81],"Whisper-hallucinated":[83],"content,":[84],"finding":[85],"38%":[87],"hallucinations":[89,109,141,167,179],"include":[90],"explicit":[91],"harms":[92],"such":[93],"perpetuating":[95],"violence,":[96],"making":[97],"up":[98],"inaccurate":[99],"associations,":[100],"implying":[102],"false":[103],"authority.":[104],"then":[106],"study":[107],"why":[108],"occur":[110,143],"by":[111,178],"observing":[112],"disparities":[114],"hallucination":[116],"rates":[117],"between":[118],"speakers":[119],"with":[120,148],"aphasia":[121],"(who":[122],"have":[123],"lowered":[125],"ability":[126],"express":[128],"themselves":[129],"using":[130],"and":[132,134,170],"voice)":[133],"control":[136],"group.":[137],"disproportionately":[142],"individuals":[145],"who":[146],"speak":[147],"longer":[149],"shares":[150],"non-vocal":[152],"durations\u2014a":[153],"common":[154],"symptom":[155],"aphasia.":[157],"call":[159],"on":[160],"practitioners":[162],"ameliorate":[164],"these":[165],"language-model-based":[166],"raise":[172],"awareness":[173],"potential":[175],"biases":[176],"amplified":[177],"downstream":[181],"applications":[182],"speech-to-text":[184],"models.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":16},{"year":2025,"cited_by_count":49},{"year":2024,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}