{"id":"https://openalex.org/W3212799896","doi":"https://doi.org/10.1109/icassp43922.2022.9746038","title":"Joint Unsupervised and Supervised Training for Multilingual ASR","display_name":"Joint Unsupervised and Supervised Training for Multilingual ASR","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3212799896","doi":"https://doi.org/10.1109/icassp43922.2022.9746038","mag":"3212799896"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746038","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746038","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5002187986","display_name":"Junwen Bai","orcid":"https://orcid.org/0000-0001-7939-4927"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Junwen Bai","raw_affiliation_strings":["Google,USA","Google, USA"],"affiliations":[{"raw_affiliation_string":"Google,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374448","display_name":"Bo Li","orcid":"https://orcid.org/0000-0002-6711-3603"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":["Google,USA","Google, USA"],"affiliations":[{"raw_affiliation_string":"Google,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433648","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-9505-1833"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Google,USA","Google, USA"],"affiliations":[{"raw_affiliation_string":"Google,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024316712","display_name":"Ankur Bapna","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ankur Bapna","raw_affiliation_strings":["Google,USA","Google, USA"],"affiliations":[{"raw_affiliation_string":"Google,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057946983","display_name":"Nikhil Siddhartha","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikhil Siddhartha","raw_affiliation_strings":["Google,USA","Google, USA"],"affiliations":[{"raw_affiliation_string":"Google,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032798707","display_name":"Khe Chai Sim","orcid":"https://orcid.org/0000-0002-0866-2223"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khe Chai Sim","raw_affiliation_strings":["Google,USA","Google, USA"],"affiliations":[{"raw_affiliation_string":"Google,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tara N. Sainath","raw_affiliation_strings":["Google,USA","Google, USA"],"affiliations":[{"raw_affiliation_string":"Google,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5002187986"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":3.8501,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.94736842,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6402","last_page":"6406"},"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":0.9973999857902527,"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"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9950000047683716,"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":0.8601787090301514},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.7288911938667297},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5917497277259827},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5414670705795288},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5058862566947937},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4686628580093384},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46139761805534363},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46026474237442017},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.44441384077072144},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4275180995464325},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.10308757424354553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8601787090301514},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.7288911938667297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5917497277259827},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5414670705795288},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5058862566947937},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4686628580093384},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46139761805534363},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46026474237442017},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.44441384077072144},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4275180995464325},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10308757424354553},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746038","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746038","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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":0.7599999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1828163288","https://openalex.org/W2127141656","https://openalex.org/W2547875792","https://openalex.org/W2842511635","https://openalex.org/W2896457183","https://openalex.org/W2914120296","https://openalex.org/W2935542736","https://openalex.org/W2963341956","https://openalex.org/W2970049541","https://openalex.org/W2973157397","https://openalex.org/W3003875258","https://openalex.org/W3016181583","https://openalex.org/W3017961061","https://openalex.org/W3025165719","https://openalex.org/W3036601975","https://openalex.org/W3037057938","https://openalex.org/W3093579165","https://openalex.org/W3094637009","https://openalex.org/W3095410713","https://openalex.org/W3097777922","https://openalex.org/W3099782249","https://openalex.org/W3104215796","https://openalex.org/W3128768055","https://openalex.org/W3131692382","https://openalex.org/W3157697407","https://openalex.org/W3160235762","https://openalex.org/W3166278947","https://openalex.org/W3167207712","https://openalex.org/W3169320628","https://openalex.org/W3186596101","https://openalex.org/W3193521535","https://openalex.org/W3197074955","https://openalex.org/W3198429080","https://openalex.org/W3202037040","https://openalex.org/W3209059054","https://openalex.org/W4210463634","https://openalex.org/W4210690962","https://openalex.org/W4226033575","https://openalex.org/W4297808394","https://openalex.org/W6631190155","https://openalex.org/W6638749077","https://openalex.org/W6729448088","https://openalex.org/W6755207826","https://openalex.org/W6767737316","https://openalex.org/W6779919476","https://openalex.org/W6780218876","https://openalex.org/W6784532283","https://openalex.org/W6784614252","https://openalex.org/W6784807880","https://openalex.org/W6788335241","https://openalex.org/W6790807788","https://openalex.org/W6799245484","https://openalex.org/W6801625237"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2005801347","https://openalex.org/W2372385138","https://openalex.org/W2186640231","https://openalex.org/W4296359239","https://openalex.org/W1557905920","https://openalex.org/W2787642437"],"abstract_inverted_index":{"Self-supervised":[0],"training":[1],"has":[2],"shown":[3],"promising":[4],"gains":[5],"in":[6,33,44,142],"pretraining":[7,36],"models":[8],"and":[9,38,58,69,73,94,107,126,157,179],"facilitating":[10],"the":[11,28,34,39,45,65,70,84,128,158,176,182],"downstream":[12],"finetuning":[13,42],"for":[14],"speech":[15],"recognition,":[16],"like":[17,167],"multilingual":[18,143],"ASR.":[19,144],"Most":[20],"existing":[21,123],"methods":[22],"adopt":[23],"a":[24,112,132],"2-stage":[25,160],"scheme":[26],"where":[27],"self-supervised":[29,71],"loss":[30,68],"is":[31,95,171],"optimized":[32],"first":[35],"stage,":[37],"standard":[40],"supervised":[41,66,183],"resumes":[43],"second":[46],"stage.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51,100],"propose":[52],"an":[53],"end-to-end":[54],"(E2E)":[55],"Joint":[56],"Unsupervised":[57],"Supervised":[59],"Training":[60],"(JUST)":[61],"method":[62,186],"to":[63],"combine":[64],"RNN-T":[67],"contrastive":[72],"masked":[74],"language":[75],"modeling":[76],"(MLM)":[77],"losses.":[78],"We":[79],"validate":[80],"its":[81],"performance":[82],"on":[83],"public":[85],"dataset":[86],"Multilingual":[87],"LibriSpeech":[88],"(MLS),":[89],"which":[90,187],"includes":[91],"8":[92],"languages":[93,141,150,166],"extremely":[96],"imbalanced.":[97],"On":[98,164],"MLS,":[99],"explore":[101],"(1)":[102],"JUST":[103,109,118],"trained":[104],"from":[105,111],"scratch,":[106],"(2)":[108],"finetuned":[110],"pretrained":[113],"checkpoint.":[114],"Experiments":[115],"show":[116],"that":[117],"can":[119],"consistently":[120],"outperform":[121],"other":[122],"state-of-the-art":[124,159],"methods,":[125],"beat":[127],"monolingual":[129,153,177],"baseline":[130,154,178],"by":[131,155,162],"significant":[133],"margin,":[134],"demonstrating":[135],"JUST\u2019s":[136],"capability":[137],"of":[138,148,175],"handling":[139],"low-resource":[140,165],"Our":[145],"average":[146,152],"WER":[147,170],"all":[149],"outperforms":[151],"33.3%,":[156],"XLSR":[161],"32%.":[163],"Polish,":[168],"our":[169],"less":[172],"than":[173],"half":[174],"even":[180],"beats":[181],"transfer":[184],"learning":[185],"uses":[188],"external":[189],"supervision.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}