{"id":"https://openalex.org/W3092459676","doi":"https://doi.org/10.1007/s10579-020-09505-5","title":"Investigating the effects of gender, dialect, and training size on the performance of Arabic speech recognition","display_name":"Investigating the effects of gender, dialect, and training size on the performance of Arabic speech recognition","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3092459676","doi":"https://doi.org/10.1007/s10579-020-09505-5","mag":"3092459676"},"language":"en","primary_location":{"id":"doi:10.1007/s10579-020-09505-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-020-09505-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-020-09505-5.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10579-020-09505-5.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018849768","display_name":"Eiman Alsharhan","orcid":"https://orcid.org/0000-0001-6351-3805"},"institutions":[{"id":"https://openalex.org/I36721946","display_name":"Kuwait University","ror":"https://ror.org/021e5j056","country_code":"KW","type":"education","lineage":["https://openalex.org/I36721946"]}],"countries":["KW"],"is_corresponding":true,"raw_author_name":"Eiman Alsharhan","raw_affiliation_strings":["Kuwait University, Kuwait City, Kuwait"],"raw_orcid":"https://orcid.org/0000-0001-6351-3805","affiliations":[{"raw_affiliation_string":"Kuwait University, Kuwait City, Kuwait","institution_ids":["https://openalex.org/I36721946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035477242","display_name":"Allan Ramsay","orcid":"https://orcid.org/0000-0002-9903-0722"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Allan Ramsay","raw_affiliation_strings":["University of Manchester, Manchester, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5018849768"],"corresponding_institution_ids":["https://openalex.org/I36721946"],"apc_list":null,"apc_paid":null,"fwci":3.5358,"has_fulltext":true,"cited_by_count":44,"citation_normalized_percentile":{"value":0.94111723,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"54","issue":"4","first_page":"975","last_page":"998"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.988099992275238,"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/T10860","display_name":"Speech and Audio Processing","score":0.9865000247955322,"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/variation","display_name":"Variation (astronomy)","score":0.7561856508255005},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7022621631622314},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.643561840057373},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6235174536705017},{"id":"https://openalex.org/keywords/formality","display_name":"Formality","score":0.5396360158920288},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.515605628490448},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3821578919887543},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3705071806907654}],"concepts":[{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.7561856508255005},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7022621631622314},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.643561840057373},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6235174536705017},{"id":"https://openalex.org/C2777159308","wikidata":"https://www.wikidata.org/wiki/Q1757948","display_name":"Formality","level":2,"score":0.5396360158920288},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.515605628490448},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3821578919887543},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3705071806907654},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10579-020-09505-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-020-09505-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-020-09505-5.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10579-020-09505-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-020-09505-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-020-09505-5.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1274170081","display_name":null,"funder_award_id":"AA01/18","funder_id":"https://openalex.org/F4320322668","funder_display_name":"Kuwait University"}],"funders":[{"id":"https://openalex.org/F4320320273","display_name":"University of Cambridge","ror":"https://ror.org/013meh722"},{"id":"https://openalex.org/F4320322668","display_name":"Kuwait University","ror":"https://ror.org/021e5j056"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3092459676.pdf","grobid_xml":"https://content.openalex.org/works/W3092459676.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W28953113","https://openalex.org/W124356247","https://openalex.org/W186053141","https://openalex.org/W190336308","https://openalex.org/W273093436","https://openalex.org/W1494198834","https://openalex.org/W1833560214","https://openalex.org/W1988885465","https://openalex.org/W1990501283","https://openalex.org/W2009639677","https://openalex.org/W2020079054","https://openalex.org/W2021513757","https://openalex.org/W2103195385","https://openalex.org/W2140231899","https://openalex.org/W2155770957","https://openalex.org/W2160802179","https://openalex.org/W2183236601","https://openalex.org/W2250224884","https://openalex.org/W2250960632","https://openalex.org/W2251224833","https://openalex.org/W2251433042","https://openalex.org/W2288402171","https://openalex.org/W2307960051","https://openalex.org/W2401273849","https://openalex.org/W2767730261","https://openalex.org/W2796873842","https://openalex.org/W2893449927","https://openalex.org/W3037190132","https://openalex.org/W3082279234","https://openalex.org/W4245136196","https://openalex.org/W4251111426","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W25517187","https://openalex.org/W2480381080","https://openalex.org/W2193232575","https://openalex.org/W2329847998","https://openalex.org/W2500726251","https://openalex.org/W4250466770","https://openalex.org/W138719379","https://openalex.org/W1838148781","https://openalex.org/W2043267429","https://openalex.org/W2061937230"],"abstract_inverted_index":{"Abstract":[0],"Research":[1],"in":[2,25,32,43,106,189,197,213,225,261],"Arabic":[3,53,99,257],"automatic":[4],"speech":[5],"recognition":[6,273],"(ASR)":[7],"is":[8,75,109,154,187,292],"constrained":[9],"by":[10,125,134,157,171],"datasets":[11],"of":[12,16,48,50,61,79,129,179,194,211,234,243,246,272],"limited":[13],"size,":[14],"and":[15,20,46,63,94,115,133,174,181,205,218],"highly":[17],"variable":[18],"content":[19],"quality.":[21],"Arabic-language":[22],"resources":[23,31],"vary":[24,41],"the":[26,44,51,80,95,142,190,198,208,232,244,269,282,312],"attributes":[27],"that":[28,110,203],"affect":[29],"language":[30],"other":[33],"languages":[34,57],"(noise,":[35],"channel,":[36],"speaker,":[37],"genre),":[38],"but":[39,67],"also":[40,145],"significantly":[42],"dialect":[45,180,206],"level":[47],"formality":[49],"spoken":[52],"they":[54],"capture.":[55],"Many":[56],"suffer":[58],"similar":[59],"levels":[60],"cross-dialect":[62,248],"cross-register":[64],"acoustic":[65,92,112,131,160,192,235],"variability,":[66],"these":[68],"effects":[69],"have":[70],"been":[71],"under-studied.":[72],"This":[73,300],"paper":[74,108],"an":[76,285],"experimental":[77],"analysis":[78],"interaction":[81,104],"between":[82,111,172,237],"classical":[83],"ASR":[84,100,298],"corpus-compensation":[85],"methods":[86],"(feature":[87],"selection,":[88,90],"data":[89,291],"gender-dependent":[91],"models)":[93],"dialect-dependent/register-dependent":[96],"variation":[97,121,183,188,212],"among":[98],"corpora.":[101],"The":[102,176],"first":[103],"studied":[105],"this":[107],"recording":[113,151],"quality":[114],"discrete":[116],"pronunciation":[117,120],"variation.":[118],"Discrete":[119],"can":[122],"be":[123,185,315],"compensated":[124,156],"using":[126],"grapheme-based":[127],"instead":[128],"phone-based":[130],"models,":[132],"filtering":[135],"out":[136,308],"speakers":[137],"with":[138],"insufficient":[139],"training":[140,290,313],"data;":[141],"latter":[143],"technique":[144],"helps":[146],"to":[147,184,222,229,252,263,276,306,316],"compensate":[148],"for":[149,241,294],"poor":[150],"quality,":[152],"which":[153],"further":[155,230],"eliminating":[158],"delta-delta":[159],"features.":[161],"All":[162],"three":[163],"techniques,":[164],"together,":[165],"reduce":[166],"Word":[167],"Error":[168],"Rate":[169],"(WER)":[170],"3.24%":[173],"5.35%.":[175],"second":[177],"aspect":[178],"register":[182],"considered":[186],"fine-grained":[191],"pronunciations":[193],"each":[195,242],"phoneme":[196],"language.":[199],"Experimental":[200],"results":[201],"prove":[202],"gender":[204,217],"are":[207,250,259],"principal":[209],"components":[210],"speech,":[214],"therefore,":[215],"building":[216,295],"dialect-specific":[219],"models":[220,239],"leads":[221],"substantial":[223],"decreases":[224],"WER.":[226],"In":[227],"order":[228,262],"explore":[231],"degree":[233],"differences":[236],"phone":[238],"required":[240],"dialects":[245,258],"Arabic,":[247],"experiments":[249],"conducted":[251],"measure":[253],"how":[254,288,309],"far":[255],"apart":[256],"acoustically":[260],"make":[264],"a":[265],"better":[266],"decision":[267],"about":[268],"minimal":[270],"number":[271],"systems":[274],"needed":[275,293],"cover":[277],"all":[278],"dialectal":[279],"Arabic.":[280],"Finally,":[281],"research":[283],"addresses":[284],"important":[286],"question:":[287],"much":[289],"efficient":[296],"speaker-independent":[297],"systems?":[299],"includes":[301],"developing":[302],"some":[303],"learning":[304],"curves":[305],"find":[307],"large":[310],"must":[311],"set":[314],"achieve":[317],"acceptable":[318],"performance.":[319]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":10}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}
