{"id":"https://openalex.org/W7224995298","doi":"https://doi.org/10.31235/osf.io/73cz6_v1","title":"Does AI transcribe every accent as General American? Variety normalization in phonetic transcription by multimodal models","display_name":"Does AI transcribe every accent as General American? Variety normalization in phonetic transcription by multimodal models","publication_year":2026,"publication_date":"2026-11-01","ids":{"openalex":"https://openalex.org/W7224995298","doi":"https://doi.org/10.31235/osf.io/73cz6_v1"},"language":"en","primary_location":{"id":"doi:10.31235/osf.io/73cz6_v1","doi":"https://doi.org/10.31235/osf.io/73cz6_v1","is_oa":true,"landing_page_url":"https://doi.org/10.31235/osf.io/73cz6_v1","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.31235/osf.io/73cz6_v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160275424","display_name":"Felipe Paula Marques","orcid":"https://orcid.org/0009-0001-5363-8986","observed_orcids":["https://orcid.org/0009-0001-5363-8986"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Felipe Paula Marques","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0001-5363-8986","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078611981","display_name":"C\u00e2ndido Samuel Fonseca de Oliveira","orcid":"https://orcid.org/0000-0001-7578-6288","observed_orcids":["https://orcid.org/0000-0001-7578-6288"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"C\u00e2ndido Oliveira","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-7578-6288","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.5845000147819519,"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"}},"topics":[{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.5845000147819519,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.21310000121593475,"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":0.16670000553131104,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/phonetic-transcription","display_name":"phonetic transcription","score":0.8149999976158142},{"id":"https://openalex.org/keywords/multimodal-language-models","display_name":"multimodal language models","score":0.7710000276565552},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.46000000834465027},{"id":"https://openalex.org/keywords/accent-variation","display_name":"accent variation","score":0.6779999732971191},{"id":"https://openalex.org/keywords/general-american","display_name":"General American","score":0.8009999990463257},{"id":"https://openalex.org/keywords/rhoticity","display_name":"rhoticity","score":0.6259999871253967},{"id":"https://openalex.org/keywords/standard-language-ideology","display_name":"standard language ideology","score":0.6190000176429749},{"id":"https://openalex.org/keywords/pronunciation-teaching","display_name":"pronunciation teaching","score":0.6520000100135803},{"id":"https://openalex.org/keywords/citation-forms","display_name":"citation forms","score":0.38600000739097595}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8364999890327454},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.8036999702453613},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7775999903678894},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.5940999984741211},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5458999872207642},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5184000134468079},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.4997999966144562},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4812000095844269},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46309998631477356},{"id":"https://openalex.org/C2777939226","wikidata":"https://www.wikidata.org/wiki/Q7976","display_name":"American English","level":2,"score":0.43309998512268066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39070001244544983},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.3889000117778778},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.3612000048160553},{"id":"https://openalex.org/C2778329345","wikidata":"https://www.wikidata.org/wiki/Q919978","display_name":"Prestige","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C148934300","wikidata":"https://www.wikidata.org/wiki/Q40998","display_name":"Phonology","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C2987567764","wikidata":"https://www.wikidata.org/wiki/Q125421","display_name":"Second language","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2574999928474426}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.31235/osf.io/73cz6_v1","doi":"https://doi.org/10.31235/osf.io/73cz6_v1","is_oa":true,"landing_page_url":"https://doi.org/10.31235/osf.io/73cz6_v1","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},{"id":"pmh:oai:share.osf.io:2db7bf50-1e9a-4a78-8f5b-6716f319fba0","doi":null,"is_oa":true,"landing_page_url":"https://osf.io/73cz6","pdf_url":null,"source":{"id":"https://openalex.org/S4306401238","display_name":"SocArXiv (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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.31235/osf.io/73cz6_v1","doi":"https://doi.org/10.31235/osf.io/73cz6_v1","is_oa":true,"landing_page_url":"https://doi.org/10.31235/osf.io/73cz6_v1","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W6947928894","https://openalex.org/W4415433461","https://openalex.org/W4385823505","https://openalex.org/W7224349301","https://openalex.org/W183403967","https://openalex.org/W2188281989","https://openalex.org/W4385822546","https://openalex.org/W1607371033","https://openalex.org/W2127611282","https://openalex.org/W4413922999"],"abstract_inverted_index":{"Multimodal":[0],"language":[1],"models":[2],"transcribe":[3],"speech":[4],"phonetically":[5],"and":[6,58,62,107,144,206,221,229],"are":[7],"alreadyproposed":[8],"for":[9],"pronunciation":[10,212],"teaching,":[11],"with":[12,68,126,224],"the":[13,30,63,69,85,87,91,111,120,133,158,169,184,196,199,201],"transcription":[14,197],"treated":[15],"as":[16],"a":[17,27,56,82,101,114,162],"neutral":[18],"record":[19],"of":[20,75,84,90,123,132,152],"thesignal.":[21],"This":[22],"study":[23,64],"tests":[24],"whether":[25],"such":[26],"model":[28,202],"preserves":[29],"variation":[31],"between":[32],"speakers":[33,47,77,93,149,185],"ormoves":[34],"it":[35],"toward":[36],"General":[37],"American":[38,127],"(GA).":[39],"Gemini":[40],"3.1":[41],"Flash-Lite":[42],"transcribed":[43],"117":[44],"SpeechAccent":[45],"Archive":[46],"in":[48,104,150,211],"five":[49],"prestige":[50],"tiers,":[51],"three":[52],"times":[53],"each,":[54],"under":[55],"standard":[57],"an":[59],"anticitation":[60],"instruction,":[61],"compared":[65],"each":[66],"output":[67],"archive's":[70],"expert":[71],"IPA.":[72],"Themodel's":[73],"transcriptions":[74,89,209],"different":[76],"were":[78],"separated":[79],"by":[80,100],"about":[81],"fifth":[83],"distancebetween":[86],"expert's":[88,112],"same":[92],"(convergence":[94],"ratio":[95],"0.20,":[96],"95%":[97],"CI[0.18,":[98],"0.22]),":[99],"similar":[102],"factor":[103],"every":[105],"tier,":[106],"lay":[108],"closer":[109],"than":[110],"to":[113,119,147,168,204,215],"GAreference":[115],"and,":[116],"above":[117],"all,":[118],"citation":[121],"forms":[122],"isolated":[124],"words,":[125],"rhoticity.":[128],"Themodel":[129],"recorded":[130,178],"none":[131],"vowel":[134],"features":[135,183],"that":[136,192,207],"marked":[137],"Australian,":[138],"New":[139],"Zealand":[140],"andSouthern":[141],"US":[142],"speech,":[143],"gave":[145],"/r/":[146],"non-rhotic":[148],"73%":[151],"contexts,":[153],"against":[154],"theexpert's":[155],"5%.":[156],"Neither":[157],"anti-citation":[159],"instruction":[160],"nor":[161],"minimal":[163],"prompt":[164],"brought":[165],"thetranscription":[166],"back":[167],"speaker.":[170],"A":[171],"larger":[172],"model,":[173],"tested":[174],"on":[175],"25":[176],"speakers,":[177],"more":[179],"localfeatures":[180],"but":[181],"also":[182],"did":[186],"not":[187],"produce.":[188],"The":[189],"article":[190],"argues":[191],"standardlanguage":[193],"ideology":[194],"enters":[195],"through":[198],"reference":[200],"applies":[203],"everyspeaker,":[205],"AI":[208],"used":[210],"teaching":[213],"need":[214],"be":[216],"checked":[217],"bylistening.":[218],"Claude":[219],"(Anthropic)":[220],"Consensus":[222],"assisted":[223],"literature":[225],"search,":[226],"analysis":[227],"scripts,revision":[228],"translation.":[230]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-11-01T00:00:00"}