{"id":"https://openalex.org/W3026041220","doi":"https://doi.org/10.21437/interspeech.2020-1470","title":"Improved Noisy Student Training for Automatic Speech Recognition","display_name":"Improved Noisy Student Training for Automatic Speech Recognition","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3026041220","doi":"https://doi.org/10.21437/interspeech.2020-1470","mag":"3026041220"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1470","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1470","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/2005.09629","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100613715","display_name":"Daniel Park","orcid":"https://orcid.org/0000-0002-1919-0460"},"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":"Daniel S. Park","raw_affiliation_strings":["Google Inc., U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., U.S.A","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 Inc., U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102792436","display_name":"Jia Ye","orcid":"https://orcid.org/0000-0002-8000-4911"},"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":"Ye Jia","raw_affiliation_strings":["Google Inc., U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100750907","display_name":"Wei Han","orcid":"https://orcid.org/0000-0002-4201-9645"},"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":"Wei Han","raw_affiliation_strings":["Google Inc., U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027763497","display_name":"Chung\u2010Cheng Chiu","orcid":"https://orcid.org/0000-0001-9729-4778"},"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":"Chung-Cheng Chiu","raw_affiliation_strings":["Google Inc., U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101706071","display_name":"Bo Li","orcid":"https://orcid.org/0000-0003-3605-9437"},"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 Inc., U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010253402","display_name":"Yonghui Wu","orcid":"https://orcid.org/0000-0002-6780-6135"},"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":"Yonghui Wu","raw_affiliation_strings":["Google Inc., U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088551093","display_name":"Quoc V. Le","orcid":"https://orcid.org/0000-0002-1087-2844"},"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":"Quoc V. Le","raw_affiliation_strings":["Google Inc., U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":228,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2817","last_page":"2821"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9923999905586243,"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/T11609","display_name":"Geophysical Methods and Applications","score":0.9718000292778015,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6029516458511353},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.48931023478507996},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4857378602027893},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4455224871635437},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4157707691192627},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.41386762261390686},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.41318392753601074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3255913257598877},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08028477430343628}],"concepts":[{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6029516458511353},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.48931023478507996},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4857378602027893},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4455224871635437},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4157707691192627},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.41386762261390686},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.41318392753601074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3255913257598877},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08028477430343628},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2020-1470","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1470","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2005.09629","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.09629","pdf_url":"https://arxiv.org/pdf/2005.09629","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2005.09629","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.09629","pdf_url":"https://arxiv.org/pdf/2005.09629","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W165878654","https://openalex.org/W1489125746","https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W1915251500","https://openalex.org/W1993660824","https://openalex.org/W2062366414","https://openalex.org/W2088622183","https://openalex.org/W2101210369","https://openalex.org/W2111316763","https://openalex.org/W2117590177","https://openalex.org/W2121879602","https://openalex.org/W2327501763","https://openalex.org/W2577366047","https://openalex.org/W2912492482","https://openalex.org/W2936774411","https://openalex.org/W2940322076","https://openalex.org/W2944255943","https://openalex.org/W2962369866","https://openalex.org/W2962907457","https://openalex.org/W2963425185","https://openalex.org/W2963920996","https://openalex.org/W2964245029","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2976223659","https://openalex.org/W2979476256","https://openalex.org/W2981952041","https://openalex.org/W2995181338","https://openalex.org/W2995746049","https://openalex.org/W2996383576","https://openalex.org/W2998532468","https://openalex.org/W3001197829","https://openalex.org/W3015265920","https://openalex.org/W3015522062","https://openalex.org/W3015995734","https://openalex.org/W3016010032","https://openalex.org/W3035160371","https://openalex.org/W3103005696","https://openalex.org/W3125709657","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4394050964","https://openalex.org/W2551249631"],"abstract_inverted_index":{"Recently,":[0],"a":[1],"semi-supervised":[2],"learning":[3],"method":[4,29],"known":[5],"as":[6,54,102,110,135],"\"noisy":[7],"student":[8,23,45],"training\"":[9],"has":[10],"been":[11],"shown":[12],"to":[13,33,62,80,118,146],"improve":[14,34,43,147],"image":[15],"classification":[16],"performance":[17],"of":[18,100,133],"deep":[19],"networks":[20],"significantly.":[21],"Noisy":[22],"training":[24,46],"is":[25],"an":[26],"iterative":[27],"self-training":[28,72],"that":[30],"leverages":[31],"augmentation":[32,56],"network":[35],"performance.":[36],"In":[37],"this":[38],"work,":[39],"we":[40,77,115],"adapt":[41],"and":[42,65,106,160],"noisy":[44],"for":[47,139],"automatic":[48],"speech":[49],"recognition,":[50],"employing":[51],"(adaptive)":[52],"SpecAugment":[53],"the":[55,67,88,96,103,107,111,123,130,136,149],"method.":[57],"We":[58,142],"find":[59],"effective":[60],"methods":[61],"filter,":[63],"balance":[64],"augment":[66],"data":[68],"generated":[69],"in":[70],"between":[71],"iterations.":[73],"By":[74],"doing":[75],"so,":[76],"are":[78,116,143],"able":[79,117,145],"obtain":[81],"word":[82],"error":[83],"rates":[84],"(WERs)":[85],"4.2%/8.6%":[86],"on":[87,122,156],"clean/noisy":[89,124,152],"LibriSpeech":[90,101,125,140,157,161],"test":[91,126,153],"sets":[92,127],"by":[93,128],"only":[94],"using":[95,129],"clean":[97],"100h":[98,158],"subset":[99,132],"supervised":[104],"set":[105,138],"rest":[108],"(860h)":[109],"unlabeled":[112,137],"set.":[113],"Furthermore,":[114],"achieve":[119],"WERs":[120,154],"1.7%/3.4%":[121],"unlab-60k":[131],"LibriLight":[134],"960h.":[141],"thus":[144],"upon":[148],"previous":[150],"state-of-the-art":[151],"achieved":[155],"(4.74%/12.20%)":[159],"(1.9%/4.1%).":[162]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":43},{"year":2022,"cited_by_count":47},{"year":2021,"cited_by_count":73},{"year":2020,"cited_by_count":24}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}