{"id":"https://openalex.org/W3165404421","doi":"https://doi.org/10.1109/taslp.2021.3138674","title":"Exploiting Adapters for Cross-Lingual Low-Resource Speech Recognition","display_name":"Exploiting Adapters for Cross-Lingual Low-Resource Speech Recognition","publication_year":2021,"publication_date":"2021-12-28","ids":{"openalex":"https://openalex.org/W3165404421","doi":"https://doi.org/10.1109/taslp.2021.3138674","mag":"3165404421"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3138674","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3138674","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5027365025","display_name":"Wenxin Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Wenxin Hou","raw_affiliation_strings":["Microsoft, Suzhou, China","TokyoInstitute of Technology, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Microsoft, Suzhou, China","institution_ids":[]},{"raw_affiliation_string":"TokyoInstitute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101557449","display_name":"Han Zhu","orcid":"https://orcid.org/0009-0002-5060-4454"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Zhu","raw_affiliation_strings":["Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100685716","display_name":"Yidong Wang","orcid":"https://orcid.org/0009-0007-9969-8259"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yidong Wang","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100700956","display_name":"Jindong Wang","orcid":"https://orcid.org/0000-0002-4833-0880"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jindong Wang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020025718","display_name":"Tao Qin","orcid":"https://orcid.org/0000-0002-9095-0776"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Qin","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023754227","display_name":"Renjun Xu","orcid":"https://orcid.org/0000-0002-7566-7948"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renjun Xu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103015161","display_name":"Takahiro Shinozaki","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Shinozaki","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5027365025"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":5.0384,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.95998769,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"30","issue":null,"first_page":"317","last_page":"329"},"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":0.9945999979972839,"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/T10028","display_name":"Topic Modeling","score":0.9941999912261963,"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/computer-science","display_name":"Computer science","score":0.8185153007507324},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.6789583563804626},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6714171171188354},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5543373227119446},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.5519869327545166},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.504177451133728},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.44188255071640015},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4415246248245239},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4411373436450958},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3833829164505005},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3359822630882263},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.10638824105262756},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.10365036129951477}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8185153007507324},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6789583563804626},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6714171171188354},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5543373227119446},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.5519869327545166},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.504177451133728},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.44188255071640015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4415246248245239},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4411373436450958},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3833829164505005},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3359822630882263},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10638824105262756},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.10365036129951477},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2021.3138674","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3138674","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:irdb.nii.ac.jp:00897:0005215465","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100865304","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307764","display_name":"Microsoft","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320322704","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960"},{"id":"https://openalex.org/F4320333993","display_name":"Microsoft Research Asia","ror":"https://ror.org/0300m5276"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":80,"referenced_works":["https://openalex.org/W1495578138","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1731081199","https://openalex.org/W2004975564","https://openalex.org/W2127141656","https://openalex.org/W2150769028","https://openalex.org/W2402146185","https://openalex.org/W2514741789","https://openalex.org/W2526425061","https://openalex.org/W2585945212","https://openalex.org/W2604763608","https://openalex.org/W2786835190","https://openalex.org/W2794363191","https://openalex.org/W2795900505","https://openalex.org/W2808640845","https://openalex.org/W2885706078","https://openalex.org/W2892009249","https://openalex.org/W2894835365","https://openalex.org/W2895531857","https://openalex.org/W2896457183","https://openalex.org/W2914120296","https://openalex.org/W2923014074","https://openalex.org/W2962780374","https://openalex.org/W2963250244","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963431393","https://openalex.org/W2964002616","https://openalex.org/W2964121744","https://openalex.org/W2964303773","https://openalex.org/W2964309797","https://openalex.org/W2964539095","https://openalex.org/W2970925270","https://openalex.org/W2971840980","https://openalex.org/W2972818416","https://openalex.org/W2996383576","https://openalex.org/W2998115938","https://openalex.org/W3007328579","https://openalex.org/W3015078597","https://openalex.org/W3015564377","https://openalex.org/W3015585292","https://openalex.org/W3030437843","https://openalex.org/W3034469191","https://openalex.org/W3034565015","https://openalex.org/W3036601975","https://openalex.org/W3096032230","https://openalex.org/W3096215352","https://openalex.org/W3099782249","https://openalex.org/W3100452485","https://openalex.org/W3110524561","https://openalex.org/W3118905363","https://openalex.org/W3153675281","https://openalex.org/W3157697407","https://openalex.org/W3161686170","https://openalex.org/W3173563729","https://openalex.org/W3194701944","https://openalex.org/W3197845195","https://openalex.org/W3198429080","https://openalex.org/W3199518308","https://openalex.org/W4210463634","https://openalex.org/W4252553876","https://openalex.org/W4294646197","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6733117838","https://openalex.org/W6736057607","https://openalex.org/W6739901393","https://openalex.org/W6750254146","https://openalex.org/W6752630080","https://openalex.org/W6755095635","https://openalex.org/W6759455113","https://openalex.org/W6759579507","https://openalex.org/W6769196770","https://openalex.org/W6771467084","https://openalex.org/W6777155081","https://openalex.org/W6780218876","https://openalex.org/W6797016654","https://openalex.org/W6801256880"],"related_works":["https://openalex.org/W4390929683","https://openalex.org/W4288365749","https://openalex.org/W2936497627","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W4321593827","https://openalex.org/W3098382480","https://openalex.org/W4287598411","https://openalex.org/W3100913109","https://openalex.org/W3198458223"],"abstract_inverted_index":{"Cross-lingual":[0],"speech":[1,29,60],"adaptation":[2],"aims":[3,110],"to":[4,13,54,97,105,111,160,182],"solve":[5],"the":[6,22,91,99,106,113,116,124,134,161],"problem":[7],"of":[8,156],"leveraging":[9],"multiple":[10],"rich-resource":[11],"languages":[12,120,132],"build":[14],"models":[15,31],"for":[16,46,57,78,177],"a":[17,37,73],"low-resource":[18,23],"target":[19,119],"language.":[20,108],"Since":[21],"language":[24],"has":[25],"limited":[26],"training":[27,103],"data,":[28],"recognition":[30],"can":[32,41,86,144,174],"easily":[33,88],"overfit.":[34],"Adapter":[35],"is":[36],"versatile":[38],"module":[39],"that":[40,67,140,169],"be":[42,87,175],"plugged":[43],"into":[44,90],"Transformer":[45,92],"parameter-efficient":[47,58],"learning.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52,71,167],"propose":[53,72],"use":[55],"adapters":[56],"cross-lingual":[59],"adaptation.":[61],"Based":[62],"on":[63,130],"our":[64],"previous":[65],"MetaAdapter":[66,94,141],"implicitly":[68],"leverages":[69,95],"adapters,":[70],"novel":[74,172],"algorithm":[75],"called":[76],"SimAdapter":[77,109,143],"explicitly":[79],"learning":[80],"knowledge":[81,101],"from":[82,102],"adapters.":[83,125],"Our":[84],"algorithms":[85,173],"integrated":[89,176],"structure.":[93],"meta-learning":[96],"transfer":[98],"general":[100],"data":[104],"test":[107],"learn":[112],"similarities":[114],"between":[115],"source":[117],"and":[118,142,149,154],"during":[121],"fine-tuning":[122,164],"using":[123],"We":[126],"conduct":[127],"extensive":[128],"experiments":[129],"five-low-resource":[131],"in":[133],"Common":[135],"Voice":[136],"dataset.":[137],"Results":[138],"demonstrate":[139],"reduce":[145],"WER":[146,185],"by":[147],"2.98%":[148],"2.55%":[150],"with":[151,180],"only":[152],"2.5%":[153],"15.5%":[155],"trainable":[157],"parameters":[158],"compared":[159],"strong":[162],"full-model":[163],"baseline.":[165],"Moreover,":[166],"show":[168],"these":[170],"two":[171],"better":[178],"performance":[179],"up":[181],"3.55%":[183],"relative":[184],"reduction.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}