{"id":"https://openalex.org/W4396882002","doi":"https://doi.org/10.48550/arxiv.2405.06150","title":"Lost in Transcription: Identifying and Quantifying the Accuracy Biases of Automatic Speech Recognition Systems Against Disfluent Speech","display_name":"Lost in Transcription: Identifying and Quantifying the Accuracy Biases of Automatic Speech Recognition Systems Against Disfluent Speech","publication_year":2024,"publication_date":"2024-05-10","ids":{"openalex":"https://openalex.org/W4396882002","doi":"https://doi.org/10.48550/arxiv.2405.06150"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2405.06150","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.06150","pdf_url":"https://arxiv.org/pdf/2405.06150","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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2405.06150","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031540690","display_name":"Dena F. Mujtaba","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mujtaba, Dena","raw_affiliation_strings":["Michigan State University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University ,","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108624212","display_name":"Nihar R. Mahapatra","orcid":"https://orcid.org/0000-0002-3821-3330","observed_orcids":["https://orcid.org/0000-0002-3821-3330"]},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahapatra, Nihar R.","raw_affiliation_strings":["Michigan State University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University ,","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098577940","display_name":"Megan Arney","orcid":"https://orcid.org/0000-0001-6749-5149","observed_orcids":["https://orcid.org/0000-0001-6749-5149"]},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arney, Megan","raw_affiliation_strings":["Michigan State University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University ,","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018623160","display_name":"J. Scott Yaruss","orcid":"https://orcid.org/0000-0003-1964-575X","observed_orcids":["https://orcid.org/0000-0003-1964-575X"]},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yaruss, J. Scott","raw_affiliation_strings":["Michigan State University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University ,","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089178997","display_name":"Hope Gerlach","orcid":"https://orcid.org/0000-0003-3810-4940","observed_orcids":["https://orcid.org/0000-0003-3810-4940"]},"institutions":[{"id":"https://openalex.org/I141649380","display_name":"Western Michigan University","ror":"https://ror.org/04j198w64","country_code":"US","type":"education","lineage":["https://openalex.org/I141649380"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerlach-Houck, Hope","raw_affiliation_strings":["Western Michigan University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Western Michigan University ,","institution_ids":["https://openalex.org/I141649380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022124364","display_name":"Caryn Herring","orcid":"https://orcid.org/0000-0003-2404-852X","observed_orcids":["https://orcid.org/0000-0003-2404-852X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Herring, Caryn","raw_affiliation_strings":["The National Association of Young People Who Stutter 1 {mujtabad ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The National Association of Young People Who Stutter 1 {mujtabad ,","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104281427","display_name":"Jia Bin","orcid":"https://orcid.org/0009-0002-2967-5039","observed_orcids":["https://orcid.org/0009-0002-2967-5039"]},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bin, Jia","raw_affiliation_strings":["Michigan State University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University ,","institution_ids":["https://openalex.org/I87216513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9945999979972839,"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":0.9945999979972839,"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/T12684","display_name":"Stuttering Research and Treatment","score":0.00430000014603138,"subfield":{"id":"https://openalex.org/subfields/3203","display_name":"Clinical 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/T12031","display_name":"Speech and dialogue systems","score":0.0003000000142492354,"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/speech-recognition","display_name":"speech recognition","score":0.9620000123977661},{"id":"https://openalex.org/keywords/stuttering","display_name":"stuttering","score":0.9509999752044678},{"id":"https://openalex.org/keywords/disfluent-speech","display_name":"disfluent speech","score":0.9919999837875366},{"id":"https://openalex.org/keywords/transcription-accuracy","display_name":"transcription accuracy","score":0.5920000076293945},{"id":"https://openalex.org/keywords/librispeech","display_name":"LibriSpeech","score":0.9150000214576721},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"word error rate","score":0.8949999809265137},{"id":"https://openalex.org/keywords/character-error-rate","display_name":"character error rate","score":0.9049999713897705},{"id":"https://openalex.org/keywords/semantic-accuracy","display_name":"semantic accuracy","score":0.8460000157356262},{"id":"https://openalex.org/keywords/inclusiveness","display_name":"inclusivity","score":0.5519999861717224},{"id":"https://openalex.org/keywords/bias-mitigation","display_name":"bias mitigation","score":0.8769999742507935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6535286903381348},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5962774753570557},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5544650554656982},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47062304615974426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4628998041152954},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16164109110832214},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2405.06150","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.06150","pdf_url":"https://arxiv.org/pdf/2405.06150","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.2405.06150","doi":"https://doi.org/10.48550/arxiv.2405.06150","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2405.06150","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2405.06150","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.06150","pdf_url":"https://arxiv.org/pdf/2405.06150","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"},"sustainable_development_goals":[{"score":0.7578999996185303,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G4366551611","display_name":"NSF Convergence Accelerator Track H: A Broad, Human-Centered, and Convergent Framework for Transforming Voice AI Accessibility for People Who Stutter","funder_award_id":"2345086","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7777948463","display_name":"NSF Convergence Accelerator Track H: Convergent, Human-Centered Design for Making Voice-Activated AI Accessible and Fair to People Who Stutter","funder_award_id":"2235916","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396882002.pdf","grobid_xml":"https://content.openalex.org/works/W4396882002.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4402111741","https://openalex.org/W4396833390","https://openalex.org/W4414893707","https://openalex.org/W7124513169","https://openalex.org/W4388483000","https://openalex.org/W4221147660","https://openalex.org/W4367309257","https://openalex.org/W7161000689","https://openalex.org/W4417079824","https://openalex.org/W7148361948"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,37,65],"recognition":[2],"(ASR)":[3],"systems,":[4],"increasingly":[5],"prevalent":[6],"in":[7,17,140,146,154,191],"education,":[8],"healthcare,":[9],"employment,":[10],"and":[11,48,71,117,128,143,188],"mobile":[12],"technology,":[13],"face":[14],"significant":[15,130,141],"challenges":[16],"inclusivity,":[18],"particularly":[19],"for":[20,161,178],"the":[21,77,121,159,175,192],"80":[22],"million-strong":[23],"global":[24],"community":[25],"of":[26,64,95,99,120],"people":[27,179],"who":[28,69,180],"stutter.":[29],"These":[30,148],"systems":[31],"often":[32],"fail":[33],"to":[34,44,86,173,184],"accurately":[35],"interpret":[36],"patterns":[38],"deviating":[39],"from":[40,67,76],"typical":[41],"fluency,":[42],"leading":[43,54],"critical":[45,152],"usability":[46,177],"issues":[47],"misinterpretations.":[49],"This":[50],"study":[51],"evaluates":[52],"six":[53],"ASRs,":[55],"analyzing":[56],"their":[57,186],"performance":[58],"on":[59],"both":[60],"a":[61,72,126,151],"real-world":[62],"dataset":[63,74],"samples":[66],"individuals":[68],"stutter":[70,181],"synthetic":[73,82],"derived":[75],"widely-used":[78],"LibriSpeech":[79],"benchmark.":[80],"The":[81,123],"dataset,":[83],"uniquely":[84],"designed":[85],"incorporate":[87],"various":[88],"stuttering":[89],"events,":[90],"enables":[91],"an":[92],"in-depth":[93],"analysis":[94],"each":[96],"ASR's":[97],"handling":[98],"disfluent":[100,137],"speech.":[101],"Our":[102],"comprehensive":[103],"assessment":[104],"includes":[105],"metrics":[106],"such":[107],"as":[108],"word":[109],"error":[110,114],"rate":[111,115],"(WER),":[112],"character":[113],"(CER),":[116],"semantic":[118,144],"accuracy":[119,131],"transcripts.":[122],"results":[124],"reveal":[125],"consistent":[127],"statistically":[129],"bias":[132,163,168],"across":[133],"all":[134],"ASRs":[135],"against":[136],"speech,":[138],"manifesting":[139],"syntactical":[142],"inaccuracies":[145],"transcriptions.":[147],"findings":[149],"highlight":[150],"gap":[153],"current":[155],"ASR":[156],"technologies,":[157],"underscoring":[158],"need":[160],"effective":[162],"mitigation":[164],"strategies.":[165],"Addressing":[166],"this":[167],"is":[169],"imperative":[170],"not":[171],"only":[172],"improve":[174],"technology's":[176],"but":[182],"also":[183],"ensure":[185],"equitable":[187],"inclusive":[189],"participation":[190],"rapidly":[193],"evolving":[194],"digital":[195],"landscape.":[196]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2024-05-14T00:00:00"}