{"id":"https://openalex.org/W3162061711","doi":"https://doi.org/10.1109/icassp39728.2021.9414291","title":"REDAT: Accent-Invariant Representation for End-To-End ASR by Domain Adversarial Training with Relabeling","display_name":"REDAT: Accent-Invariant Representation for End-To-End ASR by Domain Adversarial Training with Relabeling","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162061711","doi":"https://doi.org/10.1109/icassp39728.2021.9414291","mag":"3162061711"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414291","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":"article","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/A5079582557","display_name":"Hu Hu","orcid":"https://orcid.org/0000-0003-2101-8317"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hu Hu","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059726557","display_name":"Xuesong Yang","orcid":"https://orcid.org/0000-0001-8625-5044"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuesong Yang","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030676855","display_name":"Zeynab Raeesy","orcid":"https://orcid.org/0000-0002-7153-1963"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeynab Raeesy","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103232491","display_name":"Jinxi Guo","orcid":"https://orcid.org/0000-0001-9563-7351"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinxi Guo","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026246923","display_name":"Gokce Keskin","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gokce Keskin","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080360704","display_name":"Harish Arsikere","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harish Arsikere","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110230355","display_name":"Ariya Rastrow","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ariya Rastrow","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090454997","display_name":"Roland Maas","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roland Maas","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3584,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.93400905,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6408","last_page":"6412"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9972000122070312,"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":0.9951000213623047,"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/computer-science","display_name":"Computer science","score":0.6879318356513977},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5470671057701111},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5410067439079285},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5062614679336548},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49866461753845215},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.44556793570518494},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44225749373435974},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3006158471107483},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24561244249343872}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6879318356513977},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5470671057701111},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5410067439079285},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5062614679336548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49866461753845215},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.44556793570518494},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44225749373435974},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3006158471107483},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24561244249343872},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414291","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":[{"display_name":"Quality Education","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W143647774","https://openalex.org/W1522301498","https://openalex.org/W1710476689","https://openalex.org/W1731081199","https://openalex.org/W2121879602","https://openalex.org/W2587080466","https://openalex.org/W2603679025","https://openalex.org/W2725155646","https://openalex.org/W2796339975","https://openalex.org/W2936774411","https://openalex.org/W2938374794","https://openalex.org/W2951890332","https://openalex.org/W2962684181","https://openalex.org/W2962760690","https://openalex.org/W2962893195","https://openalex.org/W2963140444","https://openalex.org/W2963414781","https://openalex.org/W2964099675","https://openalex.org/W2964121744","https://openalex.org/W2973094925","https://openalex.org/W3007227084","https://openalex.org/W3015723617","https://openalex.org/W3015915933","https://openalex.org/W3094979069","https://openalex.org/W3096579837","https://openalex.org/W4298289240","https://openalex.org/W6631190155","https://openalex.org/W6637568146","https://openalex.org/W6637618735","https://openalex.org/W6740303850","https://openalex.org/W6748826033","https://openalex.org/W6764481040"],"related_works":["https://openalex.org/W4367680763","https://openalex.org/W2739335048","https://openalex.org/W1506224037","https://openalex.org/W4213177143","https://openalex.org/W2151922127","https://openalex.org/W4237818736","https://openalex.org/W4252005663","https://openalex.org/W2365914832","https://openalex.org/W2352261042","https://openalex.org/W2314218554"],"abstract_inverted_index":{"Accents":[0],"mismatching":[1],"is":[2,57],"a":[3,39,77],"critical":[4],"problem":[5,15],"for":[6,35],"end-to-end":[7],"ASR.":[8],"This":[9],"paper":[10],"aims":[11],"to":[12,59,118],"address":[13],"this":[14],"by":[16,69,133],"building":[17],"an":[18],"accent-robust":[19],"RNN-T":[20],"system":[21],"with":[22],"domain":[23,65],"adversarial":[24],"training":[25],"(DAT).":[26],"We":[27,47],"unveil":[28],"the":[29,36,52,61,70],"magic":[30],"behind":[31],"DAT":[32,43,56,102,132],"and":[33,112,135,143],"provide,":[34],"first":[37],"time,":[38],"theoretical":[40],"guarantee":[41],"that":[42,50,101],"learns":[44],"accent-invariant":[45],"representations.":[46],"also":[48],"prove":[49],"performing":[51],"gradient":[53],"reversal":[54],"in":[55],"equivalent":[58],"minimizing":[60],"Jensen-Shannon":[62],"divergence":[63],"between":[64],"output":[66],"distributions.":[67],"Motivated":[68],"proof":[71],"of":[72,97,141],"equivalence,":[73],"we":[74],"introduce":[75],"reDAT,":[76],"novel":[78],"technique":[79],"based":[80],"on":[81,94,109,123,138],"DAT,":[82],"which":[83],"relabels":[84],"data":[85,99],"using":[86],"either":[87],"unsupervised":[88],"clustering":[89],"or":[90],"soft":[91],"labels.":[92],"Experiments":[93],"23K":[95],"hours":[96],"multi-accent":[98],"show":[100],"achieves":[103],"competitive":[104],"results":[105],"over":[106,131],"accent-specific":[107],"baselines":[108],"both":[110],"native":[111],"non-native":[113,139],"English":[114],"accents":[115,140],"but":[116],"up":[117],"13%":[119],"relative":[120],"WER":[121],"reduction":[122],"unseen":[124],"accents;":[125],"our":[126],"reDAT":[127],"yields":[128],"further":[129],"improvements":[130],"3%":[134],"8%":[136],"relatively":[137],"American":[142],"British":[144],"English.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}