{"id":"https://openalex.org/W7130355115","doi":"https://doi.org/10.48448/2czs-sv81","title":"AfriSpeech-MultiBench: A Verticalized Multidomain Multicountry Benchmark Suite for African Accented English ASR","display_name":"AfriSpeech-MultiBench: A Verticalized Multidomain Multicountry Benchmark Suite for African Accented English ASR","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W7130355115","doi":"https://doi.org/10.48448/2czs-sv81"},"language":"en","primary_location":{"id":"doi:10.48448/2czs-sv81","doi":"https://doi.org/10.48448/2czs-sv81","is_oa":true,"landing_page_url":"https://doi.org/10.48448/2czs-sv81","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},"volume":null,"type":"other","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48448/2czs-sv81","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126280765","display_name":"Association for Computational Linguistics 2025","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Association for Computational Linguistics 2025","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119875134","display_name":"Busayo Awobade","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Awobade, Busayo","raw_affiliation_strings":["Intron"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intron","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106912628","display_name":"Alex Gichamba","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gichamba, Alex","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049570201","display_name":"Tobi Olatunji","orcid":"https://orcid.org/0009-0009-7214-2132","observed_orcids":["https://orcid.org/0009-0009-7214-2132"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Olatunji, Tobi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107568588","display_name":"Mardhiyah Sanni","orcid":null,"observed_orcids":[]},"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":"Sanni, Mardhiyah","raw_affiliation_strings":["University of Edinburgh, IntronHealth"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh, IntronHealth","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5119293823","display_name":"Gabrial Zencha Ashungafac","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210130200","display_name":"Carnegie Mellon University Africa","ror":"https://ror.org/02f33m021","country_code":"RW","type":"education","lineage":["https://openalex.org/I4210130200","https://openalex.org/I74973139"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["RW","US"],"is_corresponding":false,"raw_author_name":"Zencha Ashungafac, Gabrial","raw_affiliation_strings":["Carnegie Mellon University Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University Africa","institution_ids":["https://openalex.org/I4210130200","https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"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/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":9.999999747378752e-05,"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/T12031","display_name":"Speech and dialogue systems","score":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.824999988079071},{"id":"https://openalex.org/keywords/benchmark-suite","display_name":"benchmark suite","score":0.6010000109672546},{"id":"https://openalex.org/keywords/domain-specific-evaluation","display_name":"domain-specific evaluation","score":0.7400000095367432},{"id":"https://openalex.org/keywords/spontaneous-speech","display_name":"spontaneous speech","score":0.5839999914169312},{"id":"https://openalex.org/keywords/non-native-speech","display_name":"non-native speech","score":0.5979999899864197},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"named entity recognition","score":0.8420000076293945},{"id":"https://openalex.org/keywords/legal-discourse","display_name":"legal discourse","score":0.8669999837875366},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.550000011920929},{"id":"https://openalex.org/keywords/voice-user-interfaces","display_name":"speech interfaces","score":0.42899999022483826}],"concepts":[{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.8723000288009644},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7688999772071838},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6503000259399414},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5231999754905701},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4442000091075897},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38530001044273376},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.3723999857902527},{"id":"https://openalex.org/C2777858628","wikidata":"https://www.wikidata.org/wiki/Q1111837","display_name":"Interactive voice response","level":2,"score":0.36250001192092896},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33340001106262207},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.3010999858379364},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2906999886035919},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.29019999504089355}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48448/2czs-sv81","doi":"https://doi.org/10.48448/2czs-sv81","is_oa":true,"landing_page_url":"https://doi.org/10.48448/2czs-sv81","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"doi:10.48448/2czs-sv81","doi":"https://doi.org/10.48448/2czs-sv81","is_oa":true,"landing_page_url":"https://doi.org/10.48448/2czs-sv81","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},"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/W7160434015","https://openalex.org/W7155421752","https://openalex.org/W7077898957","https://openalex.org/W6891830335","https://openalex.org/W7166700973","https://openalex.org/W4399795448","https://openalex.org/W7220746438","https://openalex.org/W7115585917","https://openalex.org/W7131125755","https://openalex.org/W7214766044"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,16,30,127],"speech\u2011enabled":[3],"AI,":[4],"including":[5],"Google's":[6],"NotebookLM":[7],"and":[8,28,34,70,83,96,105,161,187],"OpenAI's":[9],"speech-to-speech":[10],"API,":[11],"are":[12,139],"driving":[13],"widespread":[14],"interest":[15],"voice":[17,191,199],"interfaces":[18],"across":[19,67],"sectors":[20],"such":[21],"as":[22],"finance,":[23],"health,":[24],"agritech,":[25],"legal":[26],"services,":[27],"call\u2011centers":[29],"the":[31,56],"global":[32],"north":[33],"south.":[35],"Despite":[36],"this":[37,182],"momentum,":[38],"there":[39],"exists":[40],"no":[41],"publicly":[42],"available":[43],"application-specific":[44],"model":[45],"evaluation":[46,59],"that":[47],"caters":[48],"to":[49,189,194],"Africa's":[50],"linguistic":[51],"diversity.":[52],"We":[53,86],"present":[54],"$\\textbf{AfriSpeech\u2011MultiBench}$,":[55],"first":[57],"domain\u2011specific":[58,145],"suite":[60],"for":[61,178,201],"over":[62],"100":[63],"African":[64,113,167,195],"English":[65,115,168],"accents":[66],"10+":[68],"countries":[69],"seven":[71],"application":[72],"domains:":[73],"Finance,":[74],"Legal,":[75],"Medical,":[76],"General":[77],"dialogue,":[78],"Call":[79],"Center,":[80],"Named":[81],"Entities,":[82],"Hallucination":[84],"Robustness.":[85],"benchmark":[87],"a":[88,175],"diverse":[89],"range":[90],"of":[91],"open,":[92],"closed,":[93],"unimodal":[94],"ASR":[95,125],"multimodal":[97,137],"LLM-based":[98],"speech":[99,107,116,129,155],"recognition":[100],"systems":[101],"using":[102],"both":[103],"spontaneous":[104,128],"non-spontaneous":[106],"conversations":[108],"drawn":[109],"from":[110],"various":[111],"open":[112],"accented":[114],"datasets.":[117],"Our":[118],"empirical":[119],"analysis":[120],"reveals":[121],"systematic":[122],"variation:":[123],"open\u2011source":[124],"excels":[126],"contexts":[130],"but":[131,156],"degrades":[132],"on":[133,153,166],"noisy,":[134],"non\u2011native":[135],"dialogue;":[136],"LLMs":[138],"more":[140],"accent\u2011robust":[141],"yet":[142],"struggle":[143],"with":[144,172],"named":[146],"entities;":[147],"proprietary":[148],"models":[149,164],"deliver":[150],"high":[151],"accuracy":[152,171],"clean":[154],"vary":[157],"significantly":[158],"by":[159],"country":[160],"domain.":[162],"Smaller":[163],"fine\u2011tuned":[165],"achieve":[169],"competitive":[170],"lower":[173],"latency,":[174],"practical":[176],"advantage":[177],"deployment.":[179],"By":[180],"releasing":[181],"benchmark,":[183],"we":[184],"empower":[185],"practitioners":[186],"researchers":[188],"select":[190],"technologies":[192],"suited":[193],"use\u2011cases,":[196],"fostering":[197],"inclusive":[198],"applications":[200],"undeserved":[202],"communities.":[203]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-19T00:00:00"}