{"id":"https://openalex.org/W7140628103","doi":"https://doi.org/10.48550/arxiv.2603.24549","title":"A Sociolinguistic Analysis of Automatic Speech Recognition Bias in Newcastle English","display_name":"A Sociolinguistic Analysis of Automatic Speech Recognition Bias in Newcastle English","publication_year":2026,"publication_date":"2026-03-25","ids":{"openalex":"https://openalex.org/W7140628103","doi":"https://doi.org/10.48550/arxiv.2603.24549"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2603.24549","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2603.24549","pdf_url":"https://arxiv.org/pdf/2603.24549","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-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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2603.24549","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130778377","display_name":"Dana Serditova","orcid":"https://orcid.org/0000-0003-1206-8507","observed_orcids":["https://orcid.org/0000-0003-1206-8507"]},"institutions":[{"id":"https://openalex.org/I60668342","display_name":"University of Regensburg","ror":"https://ror.org/01eezs655","country_code":"DE","type":"education","lineage":["https://openalex.org/I60668342"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Serditova, Dana","raw_affiliation_strings":["University of Regensburg , Faculty of Languages, Literature, and Cultures , Department of English and American Studies , Regensburg , 93040 , Bavaria , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Regensburg , Faculty of Languages, Literature, and Cultures , Department of English and American Studies , Regensburg , 93040 , Bavaria , Germany","institution_ids":["https://openalex.org/I60668342"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043162191","display_name":"Kevin Tang","orcid":"https://orcid.org/0000-0001-7382-9344","observed_orcids":["https://orcid.org/0000-0001-7382-9344"]},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]},{"id":"https://openalex.org/I44260953","display_name":"Heinrich Heine University D\u00fcsseldorf","ror":"https://ror.org/024z2rq82","country_code":"DE","type":"education","lineage":["https://openalex.org/I44260953"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Tang, Kevin","raw_affiliation_strings":["Heinrich Heine University D\u00fcsseldorf , Faculty of Arts and Humanities , Institute of English and American Studies , Department English Language and Linguistics , D\u00fcsseldorf , 40225 , North Rhine-Westphalia , Germany","University of Florida , Department of Linguistics , Gainesville , 32611-5454 , Florida , U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Heinrich Heine University D\u00fcsseldorf , Faculty of Arts and Humanities , Institute of English and American Studies , Department English Language and Linguistics , D\u00fcsseldorf , 40225 , North Rhine-Westphalia , Germany","institution_ids":["https://openalex.org/I44260953"]},{"raw_affiliation_string":"University of Florida , Department of Linguistics , Gainesville , 32611-5454 , Florida , U.S.A","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.5976999998092651,"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":0.5976999998092651,"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":0.3862000107765198,"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"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.009399999864399433,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dialect-variation","display_name":"dialect variation","score":0.765999972820282},{"id":"https://openalex.org/keywords/phonetic-variation","display_name":"phonetic variation","score":0.5600000023841858},{"id":"https://openalex.org/keywords/transcription-errors","display_name":"transcription errors","score":0.7239999771118164},{"id":"https://openalex.org/keywords/glottalization","display_name":"glottalization","score":0.6919999718666077},{"id":"https://openalex.org/keywords/vowel-quality","display_name":"vowel quality","score":0.9240000247955322},{"id":"https://openalex.org/keywords/phonological-variation","display_name":"phonological variation","score":0.5699999928474426},{"id":"https://openalex.org/keywords/socioeconomic-status","display_name":"socioeconomic status","score":0.675000011920929},{"id":"https://openalex.org/keywords/gender-differences","display_name":"gender differences","score":0.7710000276565552},{"id":"https://openalex.org/keywords/age-differences","display_name":"age differences","score":0.9100000262260437},{"id":"https://openalex.org/keywords/tyneside-english","display_name":"Tyneside English","score":0.7279999852180481}],"concepts":[{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.70660001039505},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.6363999843597412},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.565500020980835},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5167999863624573},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4657999873161316},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.46399998664855957},{"id":"https://openalex.org/C2777617010","wikidata":"https://www.wikidata.org/wiki/Q18957","display_name":"Mainstream","level":2,"score":0.41690000891685486},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41519999504089355},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.41110000014305115},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.38179999589920044},{"id":"https://openalex.org/C28519872","wikidata":"https://www.wikidata.org/wiki/Q160845","display_name":"Sociolinguistics","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.3797000050544739},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C2778927050","wikidata":"https://www.wikidata.org/wiki/Q7053766","display_name":"North American English","level":4,"score":0.314300000667572},{"id":"https://openalex.org/C2776567310","wikidata":"https://www.wikidata.org/wiki/Q44679","display_name":"Australian English","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C2778575526","wikidata":"https://www.wikidata.org/wiki/Q2631145","display_name":"Varieties of English","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C11693617","wikidata":"https://www.wikidata.org/wiki/Q181839","display_name":"Pragmatics","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C2777939226","wikidata":"https://www.wikidata.org/wiki/Q7976","display_name":"American English","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.26179999113082886},{"id":"https://openalex.org/C84389358","wikidata":"https://www.wikidata.org/wiki/Q1129466","display_name":"Discourse analysis","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25870001316070557},{"id":"https://openalex.org/C150321799","wikidata":"https://www.wikidata.org/wiki/Q1650645","display_name":"Mid vowel","level":4,"score":0.2574999928474426},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.2572000026702881}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2603.24549","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2603.24549","pdf_url":"https://arxiv.org/pdf/2603.24549","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-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"},{"id":"pmh:oai:share.osf.io:015bfc16-4a4e-4659-9fe7-5e6dfe0272fe","doi":null,"is_oa":true,"landing_page_url":"https://osf.io/42n9r","pdf_url":null,"source":{"id":"https://openalex.org/S4306401127","display_name":"OSF Preprints (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Project"},{"id":"doi:10.48550/arxiv.2603.24549","doi":"https://doi.org/10.48550/arxiv.2603.24549","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24549","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2603.24549","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2603.24549","pdf_url":"https://arxiv.org/pdf/2603.24549","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-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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7578999996185303}],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.6822417378425598}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140628103.pdf","grobid_xml":"https://content.openalex.org/works/W7140628103.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415432974","https://openalex.org/W7102329356","https://openalex.org/W4220768506","https://openalex.org/W4404790768","https://openalex.org/W4408353897","https://openalex.org/W7135309415","https://openalex.org/W7205345562","https://openalex.org/W7131125755","https://openalex.org/W3162386768","https://openalex.org/W4404781065"],"abstract_inverted_index":{"Automatic":[0],"Speech":[1],"Recognition":[2],"(ASR)":[3],"systems":[4,235],"are":[5,97,197],"widely":[6],"used":[7],"in":[8,32,104],"everyday":[9],"communication,":[10],"education,":[11],"healthcare,":[12],"and":[13,85,102,112,156,163,181,203,224,229,242],"industry,":[14],"yet":[15],"their":[16],"performance":[17],"remains":[18],"uneven":[19],"across":[20,171],"speakers,":[21],"particularly":[22],"when":[23],"dialectal":[24,240],"variation":[25,129,139,241],"diverges":[26],"from":[27,66,207],"the":[28,67,77,142,185,188,212,215,222],"mainstream":[29],"accents":[30],"represented":[31],"training":[33],"data.":[34,245],"This":[35],"study":[36,120,213],"investigates":[37],"ASR":[38,83,195,234],"bias":[39],"through":[40],"a":[41,47,80,87,208],"sociolinguistic":[42,209,219],"analysis":[43,89],"of":[44,50,71,79,90,121,144,187,217,226],"Newcastle":[45],"English,":[46],"regional":[48],"variety":[49],"North-East":[51],"England":[52],"that":[53,137,194,231],"has":[54],"been":[55],"shown":[56],"to":[57,106,132,150,239],"challenge":[58],"current":[59],"speech":[60,65,227,244],"recognition":[61],"technologies.":[62],"Using":[63],"spontaneous":[64],"Diachronic":[68],"Electronic":[69],"Corpus":[70],"Tyneside":[72],"English":[73],"(DECTE),":[74],"we":[75],"evaluate":[76],"output":[78],"state-of-the-art":[81],"commercial":[82],"system":[84],"conduct":[86],"fine-grained":[88],"more":[91,232],"than":[92],"3,000":[93],"transcription":[94],"errors.":[95],"Errors":[96],"classified":[98],"by":[99],"linguistic":[100],"domain":[101],"examined":[103],"relation":[105],"social":[107,172],"variables":[108],"including":[109],"gender,":[110],"age,":[111],"socioeconomic":[113],"status.":[114],"In":[115],"addition,":[116],"an":[117],"acoustic":[118],"case":[119],"selected":[122],"vowel":[123,154],"features":[124,152],"demonstrates":[125,214],"how":[126],"gradient":[127],"phonetic":[128],"contributes":[130],"directly":[131],"misrecognition.":[133],"The":[134],"results":[135],"show":[136],"phonological":[138],"accounts":[140],"for":[141,179,182],"majority":[143],"errors,":[145],"with":[146,174],"recurrent":[147],"failures":[148],"linked":[149],"dialect-specific":[151],"like":[153],"quality":[155],"glottalisation,":[157],"as":[158,160],"well":[159],"local":[161],"vocabulary":[162],"non-standard":[164],"grammatical":[165],"forms.":[166],"Error":[167],"rates":[168],"also":[169],"vary":[170],"groups,":[173],"higher":[175],"error":[176],"frequencies":[177],"observed":[178],"men":[180],"speakers":[183],"at":[184],"extremes":[186],"age":[189],"spectrum.":[190],"These":[191],"findings":[192],"indicate":[193],"errors":[196],"not":[198],"random":[199],"but":[200],"socially":[201],"patterned":[202],"can":[204],"be":[205],"explained":[206],"perspective.":[210],"Thus,":[211],"importance":[216],"incorporating":[218],"expertise":[220],"into":[221],"evaluation":[223],"development":[225],"technologies":[228],"argues":[230],"equitable":[233],"require":[236],"explicit":[237],"attention":[238],"community-based":[243]},"counts_by_year":[],"updated_date":"2026-10-27T15:51:10.671819","created_date":"2026-03-27T00:00:00"}
