{"id":"https://openalex.org/W3109234242","doi":"https://doi.org/10.1109/icassp39728.2021.9414299","title":"Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Training","display_name":"Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Training","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3109234242","doi":"https://doi.org/10.1109/icassp39728.2021.9414299","mag":"3109234242"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414299","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414299","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.13439","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035187454","display_name":"Sameer Khurana","orcid":"https://orcid.org/0000-0002-3182-1085"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sameer Khurana","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","[Mitsubishi Electric Research Laboratories (MERL), Cambridge MA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"[Mitsubishi Electric Research Laboratories (MERL), Cambridge MA, USA]","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071286568","display_name":"Niko Moritz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Niko Moritz","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","[Mitsubishi Electric Research Laboratories (MERL), Cambridge MA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"[Mitsubishi Electric Research Laboratories (MERL), Cambridge MA, USA]","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087554069","display_name":"Takaaki Hori","orcid":"https://orcid.org/0000-0003-4560-8039"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takaaki Hori","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","[Mitsubishi Electric Research Laboratories (MERL), Cambridge MA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"[Mitsubishi Electric Research Laboratories (MERL), Cambridge MA, USA]","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076453358","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-3451-171X"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Le Roux","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","[Mitsubishi Electric Research Laboratories (MERL), Cambridge MA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"[Mitsubishi Electric Research Laboratories (MERL), Cambridge MA, USA]","institution_ids":["https://openalex.org/I4210159266"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6553","last_page":"6557"},"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":0.996399998664856,"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":0.9936000108718872,"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/dropout","display_name":"Dropout (neural networks)","score":0.8104826211929321},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7428706288337708},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.7011758089065552},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.6867002844810486},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6676064133644104},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5891026854515076},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5363356471061707},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5308312773704529},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5110953450202942},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4709632992744446},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4151943027973175},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38485977053642273},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3327919840812683},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10661271214485168}],"concepts":[{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.8104826211929321},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7428706288337708},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.7011758089065552},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.6867002844810486},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6676064133644104},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5891026854515076},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5363356471061707},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5308312773704529},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5110953450202942},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4709632992744446},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4151943027973175},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38485977053642273},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3327919840812683},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10661271214485168},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414299","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414299","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"},{"id":"pmh:oai:arXiv.org:2011.13439","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.13439","pdf_url":"https://arxiv.org/pdf/2011.13439","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"},{"id":"mag:3109234242","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.13439.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2011.13439","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.13439","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/csdb-zn63","is_oa":true,"landing_page_url":"https://doi.org/10.17023/csdb-zn63","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.13439","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.13439","pdf_url":"https://arxiv.org/pdf/2011.13439","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"score":0.550000011920929,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3109234242.pdf","grobid_xml":"https://content.openalex.org/works/W3109234242.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1585385982","https://openalex.org/W1594039573","https://openalex.org/W2024490156","https://openalex.org/W2095705004","https://openalex.org/W2097089247","https://openalex.org/W2111316763","https://openalex.org/W2127141656","https://openalex.org/W2133556223","https://openalex.org/W2134800885","https://openalex.org/W2143612262","https://openalex.org/W2166637769","https://openalex.org/W2514741789","https://openalex.org/W2696967604","https://openalex.org/W2739883972","https://openalex.org/W2799473636","https://openalex.org/W2892009249","https://openalex.org/W2936774411","https://openalex.org/W2939216642","https://openalex.org/W2962684181","https://openalex.org/W2962687275","https://openalex.org/W2963431393","https://openalex.org/W2964059111","https://openalex.org/W2972818416","https://openalex.org/W2998532468","https://openalex.org/W3027083471","https://openalex.org/W3030437843","https://openalex.org/W3049397270","https://openalex.org/W3096273170","https://openalex.org/W3096338464","https://openalex.org/W3099782249","https://openalex.org/W3101648800","https://openalex.org/W3162833755","https://openalex.org/W6617145748","https://openalex.org/W6623517193","https://openalex.org/W6635184699","https://openalex.org/W6635327882","https://openalex.org/W6637618735","https://openalex.org/W6674330103","https://openalex.org/W6679855610","https://openalex.org/W6754299077","https://openalex.org/W6768222176","https://openalex.org/W6771467084","https://openalex.org/W6772883055","https://openalex.org/W6780218876","https://openalex.org/W6781650723","https://openalex.org/W6785309591"],"related_works":["https://openalex.org/W3163464943","https://openalex.org/W3162334527","https://openalex.org/W3153690224","https://openalex.org/W2749784707","https://openalex.org/W3182974804","https://openalex.org/W2972981541","https://openalex.org/W3097573669","https://openalex.org/W3011500442","https://openalex.org/W2683320792","https://openalex.org/W2963122170","https://openalex.org/W2964245029","https://openalex.org/W2766572290","https://openalex.org/W2737108017","https://openalex.org/W2796010067","https://openalex.org/W2548256801","https://openalex.org/W2981590980","https://openalex.org/W2890351244","https://openalex.org/W3136786651","https://openalex.org/W3011838870","https://openalex.org/W3205181379"],"abstract_inverted_index":{"The":[0],"performance":[1,134],"of":[2,56,132,135],"automatic":[3],"speech":[4],"recognition":[5],"(ASR)":[6],"systems":[7],"typically":[8],"degrades":[9],"significantly":[10],"when":[11],"the":[12,67,81,97,124,133],"training":[13,98,104],"and":[14,95,116],"test":[15],"data":[16,76,105,141],"domains":[17,126],"are":[18],"mismatched.":[19],"In":[20],"this":[21],"paper,":[22],"we":[23],"show":[24,127],"that":[25,128],"self-training":[26,48],"(ST)":[27],"combined":[28],"with":[29,77],"an":[30,57],"uncertainty-based":[31],"pseudo-label":[32],"filtering":[33],"approach":[34],"can":[35,142],"be":[36,143],"effectively":[37],"used":[38],"for":[39,61],"domain":[40,115],"adaptation.":[41],"We":[42],"propose":[43],"DUST,":[44],"a":[45,102,113,136],"dropout-based":[46],"uncertainty-driven":[47],"technique":[49],"which":[50,83],"uses":[51],"agreement":[52],"between":[53],"multiple":[54],"predictions":[55],"ASR":[58,88],"system":[59,137],"obtained":[60],"different":[62],"dropout":[63],"settings":[64],"to":[65,85,91,101,130],"measure":[66],"model\u2019s":[68],"uncertainty":[69],"about":[70],"its":[71],"prediction.":[72],"DUST":[73],"excludes":[74],"pseudo-labeled":[75],"high":[78],"uncertainties":[79],"from":[80],"training,":[82],"leads":[84],"substantially":[86],"improved":[87],"results":[89],"compared":[90],"ST":[92],"without":[93],"filtering,":[94],"accelerates":[96],"time":[99],"due":[100],"reduced":[103],"set.":[106],"Domain":[107],"adaptation":[108],"experiments":[109],"using":[110],"WSJ":[111],"as":[112,119,121,123],"source":[114],"TED-LIUM":[117],"3":[118],"well":[120],"SWITCHBOARD":[122],"target":[125],"up":[129],"80%":[131],"trained":[138],"on":[139],"ground-truth":[140],"recovered.":[144]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}