{"id":"https://openalex.org/W2962684181","doi":"https://doi.org/10.1109/icassp.2018.8462663","title":"Domain Adversarial Training for Accented Speech Recognition","display_name":"Domain Adversarial Training for Accented Speech Recognition","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2962684181","doi":"https://doi.org/10.1109/icassp.2018.8462663","mag":"2962684181"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5102880200","display_name":"Sining Sun","orcid":"https://orcid.org/0000-0002-2642-5096"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sining Sun","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087421101","display_name":"Ching-Feng Yeh","orcid":null},"institutions":[{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ching-Feng Yeh","raw_affiliation_strings":["Mobvoi AI Lab, Seattle, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mobvoi AI Lab, Seattle, USA","institution_ids":["https://openalex.org/I58610484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112467501","display_name":"Mei-Yuh Hwang","orcid":null},"institutions":[{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mei-Yuh Hwang","raw_affiliation_strings":["Mobvoi AI Lab, Seattle, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mobvoi AI Lab, Seattle, USA","institution_ids":["https://openalex.org/I58610484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087215613","display_name":"Mari Ostendorf","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mari Ostendorf","raw_affiliation_strings":["Department of Electrical Engineering, University of Washington, Seattle, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Washington, Seattle, USA","institution_ids":["https://openalex.org/I201448701","https://openalex.org/I58610484"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.6963,"has_fulltext":false,"cited_by_count":118,"citation_normalized_percentile":{"value":0.97817361,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4854","last_page":"4858"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9932000041007996,"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/T11309","display_name":"Music and Audio Processing","score":0.991100013256073,"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/speech-recognition","display_name":"Speech recognition","score":0.7402728199958801},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7350302934646606},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.6765531301498413},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5804013013839722},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5441218614578247},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5422149896621704},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49831461906433105},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4976847469806671},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4795648455619812},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.438005656003952},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3697963356971741},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3534417152404785},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13479125499725342},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12826749682426453}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7402728199958801},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7350302934646606},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.6765531301498413},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5804013013839722},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5441218614578247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5422149896621704},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49831461906433105},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4976847469806671},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4795648455619812},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.438005656003952},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3697963356971741},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3534417152404785},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13479125499725342},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12826749682426453},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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","id":"https://metadata.un.org/sdg/4","score":0.6499999761581421}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1731081199","https://openalex.org/W1882958252","https://openalex.org/W1975113979","https://openalex.org/W2110073835","https://openalex.org/W2125107268","https://openalex.org/W2146871184","https://openalex.org/W2160815625","https://openalex.org/W2510867321","https://openalex.org/W2512655038","https://openalex.org/W2514741789","https://openalex.org/W2584667682","https://openalex.org/W2587080466","https://openalex.org/W2587088898","https://openalex.org/W2593768305","https://openalex.org/W2619710258","https://openalex.org/W2680270903","https://openalex.org/W2749784707","https://openalex.org/W2962894366","https://openalex.org/W4297664233","https://openalex.org/W4320013936","https://openalex.org/W6676769065","https://openalex.org/W6787772879"],"related_works":["https://openalex.org/W2374317326","https://openalex.org/W2990005675","https://openalex.org/W2031478549","https://openalex.org/W2163874654","https://openalex.org/W3211393740","https://openalex.org/W3208049411","https://openalex.org/W3022908591","https://openalex.org/W2946768379","https://openalex.org/W4285706568","https://openalex.org/W2134950286"],"abstract_inverted_index":{"In":[0,18,64],"this":[1],"paper,":[2],"we":[3,39,70,84,124],"propose":[4],"a":[5,45,50,106],"domain":[6,27,34,51],"adversarial":[7,52],"training":[8,53,115],"(DAT)":[9,54],"algorithm":[10],"to":[11,20,56,60,76,130],"alleviate":[12],"the":[13,22,41,58,90,95,120],"accented":[14,91,121,134],"speech":[15,135],"recognition":[16],"problem.":[17],"order":[19],"reduce":[21],"mismatch":[23],"between":[24],"labeled":[25],"source":[26],"data":[28,35,101],"(\u201cstandard\u201d":[29],"accent)":[30],"and":[31],"unlabeled":[32],"target":[33],"(with":[36],"heavy":[37],"accents),":[38],"augment":[40],"learning":[42,132],"objective":[43,55],"for":[44,133],"Kaldi":[46],"TDNN":[47],"network":[48],"with":[49,66,94,114],"encourage":[57],"model":[59],"learn":[61],"accent-invariant":[62],"features.":[63],"experiments":[65],"three":[67],"Mandarin":[68],"accents,":[69],"show":[71],"that":[72,126],"DAT":[73,109,127],"yields":[74],"up":[75],"7.45%":[77],"relative":[78],"character":[79],"error":[80],"rate":[81],"reduction":[82],"when":[83,110],"do":[85],"not":[86],"have":[87],"transcriptions":[88,118],"of":[89],"speech,":[92],"compared":[93],"baseline":[96],"trained":[97],"on":[98,119],"standard":[99],"accent":[100],"only.":[102],"We":[103],"also":[104],"find":[105,125],"benefit":[107],"from":[108,116],"used":[111],"in":[112],"combination":[113],"automatic":[117],"data.":[122],"Furthermore,":[123],"is":[128],"superior":[129],"multi-task":[131],"recognition.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}