{"id":"https://openalex.org/W3197242296","doi":"https://doi.org/10.21437/interspeech.2021-1075","title":"Layer-Wise Fast Adaptation for End-to-End Multi-Accent Speech Recognition","display_name":"Layer-Wise Fast Adaptation for End-to-End Multi-Accent Speech Recognition","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197242296","doi":"https://doi.org/10.21437/interspeech.2021-1075","mag":"3197242296"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1075","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2204.09883","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086338661","display_name":"Xun Gong","orcid":"https://orcid.org/0000-0002-3364-8407"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Gong","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Department of Computer Science and Engineering Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Department of Computer Science and Engineering Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103070663","display_name":"Yizhou Lu","orcid":"https://orcid.org/0000-0003-1399-8079"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhou Lu","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Department of Computer Science and Engineering Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Department of Computer Science and Engineering Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102974956","display_name":"Zhikai Zhou","orcid":"https://orcid.org/0000-0002-4626-2677"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhikai Zhou","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Department of Computer Science and Engineering Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Department of Computer Science and Engineering Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Department of Computer Science and Engineering Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Department of Computer Science and Engineering Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1274","last_page":"1278"},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9916999936103821,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9916999936103821,"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/stress","display_name":"Stress (linguistics)","score":0.8467274308204651},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.695518434047699},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6788577437400818},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5696076154708862},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5364765524864197},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.43130043148994446},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4310370683670044},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4099904000759125},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3518822193145752},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12718072533607483}],"concepts":[{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.8467274308204651},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.695518434047699},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6788577437400818},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5696076154708862},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5364765524864197},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.43130043148994446},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4310370683670044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4099904000759125},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3518822193145752},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12718072533607483},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2021-1075","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2204.09883","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.09883","pdf_url":"https://arxiv.org/pdf/2204.09883","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2204.09883","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.09883","pdf_url":"https://arxiv.org/pdf/2204.09883","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6800000071525574}],"awards":[{"id":"https://openalex.org/G1899722019","display_name":"\u6df1\u5ea6\u5b66\u4e60\u8bed\u97f3\u8bc6\u522b\u4e2d\u7684\u5feb\u901f\u9ad8\u6548\u81ea\u9002\u5e94\u65b9\u6cd5\u7814\u7a76","funder_award_id":"62071288","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G257170","display_name":null,"funder_award_id":"U1736202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3197242296.pdf","grobid_xml":"https://content.openalex.org/works/W3197242296.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1513820424","https://openalex.org/W2397381476","https://openalex.org/W2402146185","https://openalex.org/W2405866807","https://openalex.org/W2526425061","https://openalex.org/W2587080466","https://openalex.org/W2889494795","https://openalex.org/W2892009249","https://openalex.org/W2913244614","https://openalex.org/W2936774411","https://openalex.org/W2938374794","https://openalex.org/W2962780374","https://openalex.org/W2962893195","https://openalex.org/W2963211188","https://openalex.org/W2963403868","https://openalex.org/W2963979492","https://openalex.org/W2964099675","https://openalex.org/W2964303773","https://openalex.org/W2970925270","https://openalex.org/W2971840980","https://openalex.org/W2972539100","https://openalex.org/W2972818416","https://openalex.org/W2973094925","https://openalex.org/W3010079431","https://openalex.org/W3096122506","https://openalex.org/W3160475509","https://openalex.org/W3162508345","https://openalex.org/W3163152557","https://openalex.org/W4308252168","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2351687372","https://openalex.org/W2004087835","https://openalex.org/W2314871050","https://openalex.org/W4367680763"],"abstract_inverted_index":{"Accent":[0],"variability":[1],"has":[2,49],"posed":[3],"a":[4,62],"huge":[5],"challenge":[6],"to":[7,57,144,177],"automatic":[8],"speech":[9],"recognition~(ASR)":[10],"modeling.":[11],"Although":[12],"one-hot":[13],"accent":[14,29,38,46,80,83,103,121,136,142,147,169],"vector":[15],"based":[16],"adaptation":[17,65,98,131,155],"systems":[18],"are":[19],"commonly":[20],"used,":[21],"they":[22],"require":[23],"prior":[24],"knowledge":[25],"about":[26],"the":[27,69,82,87,97,101,107,116,126,130,133,153,167,172,178],"target":[28],"and":[30,85,105,138,159,171],"cannot":[31],"handle":[32],"unseen":[33],"accents.":[34],"Furthermore,":[35],"simply":[36],"concatenating":[37],"embeddings":[39],"does":[40],"not":[41],"make":[42],"good":[43],"use":[44],"of":[45,119,129,135,141],"knowledge,":[47],"which":[48],"limited":[50],"improvements.":[51],"In":[52],"this":[53],"work,":[54],"we":[55],"aim":[56],"tackle":[58],"these":[59],"problems":[60],"with":[61],"novel":[63],"layer-wise":[64],"structure":[66,99,156],"injected":[67],"into":[68,111],"E2E":[70],"ASR":[71,88],"model":[72,89],"encoder.":[73],"The":[74],"adapter":[75],"layer":[76],"encodes":[77],"an":[78,95,112],"arbitrary":[79],"in":[81,90],"space":[84],"assists":[86],"recognizing":[91],"accented":[92],"speech.":[93],"Given":[94],"utterance,":[96],"extracts":[100],"corresponding":[102],"information":[104],"transforms":[106],"input":[108],"acoustic":[109],"feature":[110,114],"accent-related":[113],"through":[115],"linear":[117],"combination":[118],"all":[120],"bases.":[122],"We":[123],"further":[124],"explore":[125],"injection":[127],"position":[128],"layer,":[132],"number":[134],"bases,":[137],"different":[139],"types":[140],"bases":[143],"achieve":[145],"better":[146],"adaptation.":[148],"Experimental":[149],"results":[150],"show":[151],"that":[152],"proposed":[154],"brings":[157],"12\\%":[158],"10\\%":[160],"relative":[161],"word":[162],"error":[163],"rate~(WER)":[164],"reduction":[165],"on":[166],"AESRC2020":[168],"dataset":[170],"Librispeech":[173],"dataset,":[174],"respectively,":[175],"compared":[176],"baseline.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":5}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}