{"id":"https://openalex.org/W4402115973","doi":"https://doi.org/10.21437/interspeech.2024-2300","title":"Quantification of stylistic differences in human- and ASR-produced transcripts of African American English","display_name":"Quantification of stylistic differences in human- and ASR-produced transcripts of African American English","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402115973","doi":"https://doi.org/10.21437/interspeech.2024-2300"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-2300","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2024-2300","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.03059","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068873129","display_name":"Annika Heuser","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Annika Heuser","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086480059","display_name":"Tyler Kendall","orcid":"https://orcid.org/0000-0002-0989-1765"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tyler Kendall","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079205543","display_name":"Miguel del R\u00edo","orcid":"https://orcid.org/0009-0005-3596-463X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miguel del Rio","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092964180","display_name":"Quinn McNamara","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quinn McNamara","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070176712","display_name":"Nishchal Bhandari","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nishchal Bhandari","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010857889","display_name":"Corey Miller","orcid":"https://orcid.org/0000-0003-2190-2583"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Corey Miller","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5037359921","display_name":"Mig\u00fcel Jett\u00e9","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mig\u00fcel Jett\u00e9","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5068873129"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3296,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.6516173,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4538","last_page":"4542"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"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":0.9983999729156494,"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/T10860","display_name":"Speech and Audio Processing","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9474999904632568,"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/orthography","display_name":"Orthography","score":0.7829524278640747},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6575742959976196},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6310815215110779},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5544652938842773},{"id":"https://openalex.org/keywords/american-english","display_name":"American English","score":0.5433242917060852},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5326496958732605},{"id":"https://openalex.org/keywords/conflation","display_name":"Conflation","score":0.529628336429596},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5055410861968994},{"id":"https://openalex.org/keywords/lexical-diversity","display_name":"Lexical diversity","score":0.437965989112854},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.42582300305366516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42547422647476196},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.39513716101646423},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.08087953925132751}],"concepts":[{"id":"https://openalex.org/C150670947","wikidata":"https://www.wikidata.org/wiki/Q43091","display_name":"Orthography","level":3,"score":0.7829524278640747},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6575742959976196},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6310815215110779},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5544652938842773},{"id":"https://openalex.org/C2777939226","wikidata":"https://www.wikidata.org/wiki/Q7976","display_name":"American English","level":2,"score":0.5433242917060852},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5326496958732605},{"id":"https://openalex.org/C130440534","wikidata":"https://www.wikidata.org/wiki/Q14946528","display_name":"Conflation","level":2,"score":0.529628336429596},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5055410861968994},{"id":"https://openalex.org/C2781202465","wikidata":"https://www.wikidata.org/wiki/Q18346297","display_name":"Lexical diversity","level":3,"score":0.437965989112854},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.42582300305366516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42547422647476196},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.39513716101646423},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.08087953925132751},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2024-2300","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2024-2300","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2409.03059","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.03059","pdf_url":"https://arxiv.org/pdf/2409.03059","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.03059","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.03059","pdf_url":"https://arxiv.org/pdf/2409.03059","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402115973.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2058252362","https://openalex.org/W2186092498","https://openalex.org/W1982687909","https://openalex.org/W2352149790","https://openalex.org/W2008166176","https://openalex.org/W1984630168","https://openalex.org/W2373256103","https://openalex.org/W4245621531","https://openalex.org/W1539211164","https://openalex.org/W2895592889"],"abstract_inverted_index":{"Common":[0],"measures":[1],"of":[2,9,23,72,84,87,105,133],"accuracy":[3],"used":[4],"to":[5,61],"assess":[6],"the":[7,59,70,103,134,138],"performance":[8,39],"automatic":[10],"speech":[11,54,60],"recognition":[12],"(ASR)":[13],"systems,":[14],"as":[15,17,28,66],"well":[16,110],"human":[18,141],"transcribers,":[19],"conflate":[20],"multiple":[21],"sources":[22],"error.":[24],"Stylistic":[25],"differences,":[26],"such":[27],"verbatim":[29,95],"vs":[30],"non-verbatim,":[31],"can":[32,112],"play":[33],"a":[34,131],"significant":[35],"role":[36],"in":[37],"ASR":[38,128],"evaluation":[40],"when":[41],"differences":[42,74],"exist":[43],"between":[44,75],"training":[45,139],"and":[46,81,97,122],"test":[47],"datasets.":[48],"The":[49,120],"problem":[50],"is":[51,64],"compounded":[52],"for":[53],"from":[55],"underrepresented":[56],"varieties,":[57],"where":[58],"orthography":[62],"mapping":[63],"not":[65],"standardized.":[67],"We":[68],"categorize":[69],"kinds":[71],"stylistic":[73],"6":[76],"transcription":[77],"versions,":[78],"4":[79],"human-":[80],"2":[82],"ASR-produced,":[83],"10":[85],"hours":[86],"African":[88],"American":[89],"English":[90],"(AAE)":[91],"speech.":[92],"Focusing":[93],"on":[94],"features":[96],"AAE":[98],"morphosyntactic":[99],"features,":[100],"we":[101],"investigate":[102],"interactions":[104],"these":[106],"categories":[107],"with":[108],"how":[109,127],"transcripts":[111],"be":[113],"compared":[114],"via":[115],"word":[116],"error":[117],"rate":[118],"(WER).":[119],"results,":[121],"overall":[123],"analysis,":[124],"help":[125],"clarify":[126],"outputs":[129],"are":[130],"function":[132],"decisions":[135],"made":[136],"by":[137],"data's":[140],"transcribers.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}