{"id":"https://openalex.org/W4372341945","doi":"https://doi.org/10.1109/icassp49357.2023.10095057","title":"The Edinburgh International Accents of English Corpus: Towards the Democratization of English ASR","display_name":"The Edinburgh International Accents of English Corpus: Towards the Democratization of English ASR","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372341945","doi":"https://doi.org/10.1109/icassp49357.2023.10095057"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095057","is_oa":true,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095057","pdf_url":"https://ieeexplore.ieee.org/ielx7/10094559/10094560/10095057.pdf","source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/10094559/10094560/10095057.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053704856","display_name":"Ramon Sanabria","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Ramon Sanabria","raw_affiliation_strings":["The University of Edinburgh,School of Informatics","School of Informatics, The University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"The University of Edinburgh,School of Informatics","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"School of Informatics, The University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018769709","display_name":"Nikolay Bogoychev","orcid":"https://orcid.org/0000-0003-4373-5261"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nikolay Bogoychev","raw_affiliation_strings":["The University of Edinburgh,School of Informatics","School of Informatics, The University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"The University of Edinburgh,School of Informatics","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"School of Informatics, The University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069351770","display_name":"Nina Markl","orcid":"https://orcid.org/0000-0001-9906-9961"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nina Markl","raw_affiliation_strings":["The University of Edinburgh,School of Informatics","School of Informatics, The University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"The University of Edinburgh,School of Informatics","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"School of Informatics, The University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066016980","display_name":"Andrea Carmantini","orcid":"https://orcid.org/0000-0001-9016-5092"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrea Carmantini","raw_affiliation_strings":["The University of Edinburgh,School of Informatics","School of Informatics, The University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"The University of Edinburgh,School of Informatics","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"School of Informatics, The University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044666169","display_name":"Ond\u0159ej Klejch","orcid":"https://orcid.org/0000-0001-5495-967X"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ondrej Klejch","raw_affiliation_strings":["The University of Edinburgh,School of Informatics","School of Informatics, The University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"The University of Edinburgh,School of Informatics","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"School of Informatics, The University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102911387","display_name":"Peter Bell","orcid":"https://orcid.org/0000-0002-9597-9615"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Bell","raw_affiliation_strings":["The University of Edinburgh,School of Informatics","School of Informatics, The University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"The University of Edinburgh,School of Informatics","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"School of Informatics, The University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5053704856"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":2.4878,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.91104188,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T12031","display_name":"Speech and dialogue systems","score":0.998199999332428,"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":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6143800020217896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5556349158287048},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5255226492881775},{"id":"https://openalex.org/keywords/varieties-of-english","display_name":"Varieties of English","score":0.5057621002197266},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.503724992275238},{"id":"https://openalex.org/keywords/american-english","display_name":"American English","score":0.48689332604408264},{"id":"https://openalex.org/keywords/british-english","display_name":"British English","score":0.4668937921524048},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.46590739488601685},{"id":"https://openalex.org/keywords/english-language","display_name":"English language","score":0.4453830122947693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6143800020217896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5556349158287048},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5255226492881775},{"id":"https://openalex.org/C2778575526","wikidata":"https://www.wikidata.org/wiki/Q2631145","display_name":"Varieties of English","level":2,"score":0.5057621002197266},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.503724992275238},{"id":"https://openalex.org/C2777939226","wikidata":"https://www.wikidata.org/wiki/Q7976","display_name":"American English","level":2,"score":0.48689332604408264},{"id":"https://openalex.org/C2779855358","wikidata":"https://www.wikidata.org/wiki/Q7979","display_name":"British English","level":2,"score":0.4668937921524048},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.46590739488601685},{"id":"https://openalex.org/C2987496018","wikidata":"https://www.wikidata.org/wiki/Q1860","display_name":"English language","level":2,"score":0.4453830122947693},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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":"doi:10.1109/icassp49357.2023.10095057","is_oa":true,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095057","pdf_url":"https://ieeexplore.ieee.org/ielx7/10094559/10094560/10095057.pdf","source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/f8ba3107-f4d8-4498-9538-585ca89afa32","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f8ba3107-f4d8-4498-9538-585ca89afa32","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":"Sanabria, R, Bogoychev, N, Markl, N, Carmantini, A, Klejch, O & Bell, P 2023, The Edinburgh International Accents of English Corpus: Towards the Democratization of English ASR. in ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, pp. 1-5, 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Rhodes Island, Greece, 4/06/23. https://doi.org/10.1109/ICASSP49357.2023.10095057","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"doi:10.1109/icassp49357.2023.10095057","is_oa":true,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095057","pdf_url":"https://ieeexplore.ieee.org/ielx7/10094559/10094560/10095057.pdf","source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4372341945.pdf","grobid_xml":"https://content.openalex.org/works/W4372341945.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W14965987","https://openalex.org/W28881571","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W2024490156","https://openalex.org/W2134800885","https://openalex.org/W2166637769","https://openalex.org/W2288371874","https://openalex.org/W2888954148","https://openalex.org/W2954930777","https://openalex.org/W2995181338","https://openalex.org/W3012624518","https://openalex.org/W3030437843","https://openalex.org/W3031202003","https://openalex.org/W3032558098","https://openalex.org/W3036601975","https://openalex.org/W3037831233","https://openalex.org/W3096755600","https://openalex.org/W3133702157","https://openalex.org/W3143367551","https://openalex.org/W3157428800","https://openalex.org/W3160475509","https://openalex.org/W3167533889","https://openalex.org/W3198654230","https://openalex.org/W3198771897","https://openalex.org/W3204917342","https://openalex.org/W4206413123","https://openalex.org/W4283161703","https://openalex.org/W4285058140","https://openalex.org/W4300939116","https://openalex.org/W4311000453","https://openalex.org/W6631362777","https://openalex.org/W6633847657","https://openalex.org/W6656414902","https://openalex.org/W6679855610","https://openalex.org/W6771467084","https://openalex.org/W6778691839","https://openalex.org/W6780218876","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2286392508","https://openalex.org/W2378999084","https://openalex.org/W2392275531","https://openalex.org/W2352655633","https://openalex.org/W2183577492","https://openalex.org/W3012638947","https://openalex.org/W4246736990","https://openalex.org/W4285313728","https://openalex.org/W1976025275","https://openalex.org/W2906788696"],"abstract_inverted_index":{"English":[0,41,65,83,122,145,181,199,237],"is":[1],"the":[2,8,36,47,62,70,74,92,173],"most":[3],"widely":[4],"spoken":[5,67],"language":[6,21],"in":[7,22,40,170,192],"world,":[9],"used":[10],"daily":[11],"by":[12],"millions":[13],"of":[14,33,64,77,82,95,101,116,121,128,143,157,163,236],"people":[15],"as":[16,66],"a":[17,27,113,124,190,233],"first":[18,75,117],"or":[19],"second":[20],"many":[23,31,38],"different":[24],"contexts.":[25],"As":[26],"result,":[28],"there":[29],"are":[30,51,209],"varieties":[32,120,238],"English.":[34],"Although":[35],"great":[37],"advances":[39],"automatic":[42],"speech":[43,243],"recognition":[44],"(ASR)":[45],"over":[46],"past":[48],"decades,":[49],"results":[50],"usually":[52],"reported":[53],"based":[54],"on":[55,132,153,179,194,211,232],"test":[56],"datasets":[57],"which":[58],"fail":[59],"to":[60,89,172,239],"represent":[61,91],"diversity":[63,94],"today":[68],"around":[69],"globe.":[71],"We":[72,223],"present":[73],"release":[76],"The":[78,148],"Edinburgh":[79],"International":[80],"Accents":[81],"Corpus":[84],"(EdAcc).":[85],"This":[86],"dataset":[87],"attempts":[88],"better":[90],"wide":[93,114],"English,":[96],"encompassing":[97],"almost":[98],"40":[99],"hours":[100,156],"dyadic":[102],"video":[103],"call":[104],"conversations":[105],"between":[106],"friends.":[107],"Unlike":[108],"other":[109],"datasets,":[110],"EdAcc":[111,140],"includes":[112],"range":[115,235],"and":[118,123,135,197,206],"second-language":[119],"linguistic":[125,202],"background":[126],"profile":[127],"each":[129],"speaker.":[130],"Results":[131],"latest":[133],"public,":[134],"commercial":[136],"models":[137],"show":[138],"that":[139,225],"highlights":[141],"shortcomings":[142],"current":[144],"ASR":[146],"models.":[147],"best":[149],"performing":[150],"model,":[151],"trained":[152],"680":[154],"thousand":[155],"transcribed":[158],"data,":[159],"obtains":[160],"an":[161],"average":[162],"19.7%":[164],"word":[165],"error":[166],"rate":[167],"(WER)":[168],"\u2013":[169],"contrast":[171],"2.7%":[174],"WER":[175],"obtained":[176],"when":[177],"evaluated":[178],"US":[180],"clean":[182],"read":[183],"speech.":[184],"Across":[185],"all":[186],"models,":[187],"we":[188],"observe":[189],"drop":[191],"performance":[193],"Indian,":[195],"Jamaican,":[196],"Nigerian":[198],"speakers.":[200],"Recordings,":[201],"backgrounds,":[203],"data":[204],"statement,":[205],"evaluation":[207],"scripts":[208],"released":[210],"our":[212],"website":[213],"under":[214],"CC-BY-SA":[215],"<sup":[216,220],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[217,221],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[218],"license.":[219],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[222],"hope":[224],"this":[226],"work":[227],"will":[228],"encourage":[229],"future":[230],"research":[231],"wider":[234],"create":[240],"more":[241],"accessible":[242],"technologies.":[244]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}
