{"id":"https://openalex.org/W3163865502","doi":"https://doi.org/10.1109/icassp39728.2021.9413952","title":"Multi-Dialect Speech Recognition in English Using Attention on Ensemble of Experts","display_name":"Multi-Dialect Speech Recognition in English Using Attention on Ensemble of Experts","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163865502","doi":"https://doi.org/10.1109/icassp39728.2021.9413952","mag":"3163865502"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101814582","display_name":"Amit Das","orcid":"https://orcid.org/0000-0001-7733-2976"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amit Das","raw_affiliation_strings":["Microsoft Speech and Language Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Speech and Language Group","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047826067","display_name":"Kshitiz Kumar","orcid":"https://orcid.org/0000-0003-2728-2493"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kshitiz Kumar","raw_affiliation_strings":["Microsoft Speech and Language Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Speech and Language Group","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101674460","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0002-3101-7011"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Wu","raw_affiliation_strings":["Microsoft Speech and Language Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Speech and Language Group","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":3.0771,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.93221456,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6244","last_page":"6248"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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":0.9973999857902527,"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":0.7947244644165039},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7046591639518738},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.596427857875824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5863796472549438},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5863151550292969},{"id":"https://openalex.org/keywords/ensemble-forecasting","display_name":"Ensemble forecasting","score":0.5548129677772522},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5392547845840454},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5327361226081848},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.5295817852020264},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.526052713394165},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5022296905517578},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5014209747314453},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.434886634349823},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32228267192840576},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15273213386535645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7947244644165039},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7046591639518738},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.596427857875824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5863796472549438},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5863151550292969},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.5548129677772522},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5392547845840454},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5327361226081848},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.5295817852020264},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.526052713394165},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5022296905517578},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5014209747314453},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.434886634349823},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32228267192840576},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15273213386535645},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W5524598","https://openalex.org/W60702959","https://openalex.org/W143647774","https://openalex.org/W1995562189","https://openalex.org/W2025198378","https://openalex.org/W2038375792","https://openalex.org/W2064675550","https://openalex.org/W2092845679","https://openalex.org/W2094035326","https://openalex.org/W2115730999","https://openalex.org/W2146635662","https://openalex.org/W2147768505","https://openalex.org/W2213952365","https://openalex.org/W2283606699","https://openalex.org/W2294108103","https://openalex.org/W2294543795","https://openalex.org/W2346488894","https://openalex.org/W2396384435","https://openalex.org/W2405866807","https://openalex.org/W2603679025","https://openalex.org/W2613380040","https://openalex.org/W2735006420","https://openalex.org/W2889494795","https://openalex.org/W2891628540","https://openalex.org/W2893449927","https://openalex.org/W2913340405","https://openalex.org/W2936727307","https://openalex.org/W2940131043","https://openalex.org/W2962893195","https://openalex.org/W2964002616","https://openalex.org/W2964084166","https://openalex.org/W2964099675","https://openalex.org/W2964138484","https://openalex.org/W6688428952","https://openalex.org/W6696757691","https://openalex.org/W6713969595","https://openalex.org/W6737782670"],"related_works":["https://openalex.org/W2794896638","https://openalex.org/W2891633941","https://openalex.org/W3202800081","https://openalex.org/W3101614107","https://openalex.org/W1909207154","https://openalex.org/W2594897229","https://openalex.org/W4390971112","https://openalex.org/W3036530763","https://openalex.org/W3124390867","https://openalex.org/W1514365828"],"abstract_inverted_index":{"In":[0,47],"the":[1,78,81,162],"presence":[2],"of":[3,7,69,80,122,129],"a":[4,16,24,54,88,99,113],"wide":[5],"variety":[6],"dialects,":[8],"training":[9,23],"dialect-specific":[10,70],"models":[11,71,124],"for":[12,57],"each":[13],"dialect":[14],"is":[15,28],"demanding":[17],"task.":[18],"Previous":[19],"studies":[20,34],"have":[21,35],"explored":[22],"single":[25,55],"model":[26,56,100,115,150],"that":[27,101,146],"robust":[29],"across":[30],"multiple":[31],"dialects.":[32],"These":[33],"used":[36],"either":[37],"multi-condition":[38,117],"training,":[39],"multi-task":[40,110],"learning,":[41],"end-to-end":[42],"modeling,":[43],"or":[44],"ensemble":[45,62,68],"modeling.":[46,63],"this":[48],"study,":[49],"we":[50,65,75,97],"further":[51],"explore":[52],"using":[53,61,83,109,116],"multi-dialect":[58],"speech":[59,130],"recognition":[60],"First,":[64],"build":[66],"an":[67,152],"(or":[72],"experts).":[73],"Then":[74],"linearly":[76],"combine":[77],"outputs":[79],"experts":[82],"attention":[84],"weights":[85],"generated":[86],"by":[87],"long":[89],"short-term":[90],"memory":[91],"(LSTM)":[92],"network.":[93],"For":[94],"comparison":[95],"purposes,":[96],"train":[98,120],"jointly":[102],"learns":[103],"to":[104,161],"recognize":[105],"and":[106,112,140],"classify":[107],"dialects":[108],"learning":[111],"second":[114],"training.":[118],"We":[119],"all":[121],"these":[123],"with":[125],"about":[126],"60,000":[127],"hours":[128],"data":[131],"collected":[132],"in":[133],"American":[134],"English,":[135,137,139],"Canadian":[136],"British":[138],"Australian":[141],"English.":[142],"Experimental":[143],"results":[144],"reveal":[145],"our":[147],"best":[148],"proposed":[149],"achieved":[151],"average":[153],"4.74%":[154],"word":[155],"error":[156],"rate":[157],"reduction":[158],"(WERR)":[159],"compared":[160],"strong":[163],"baseline":[164],"model.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}