{"id":"https://openalex.org/W4385822844","doi":"https://doi.org/10.21437/interspeech.2023-2205","title":"Learning When to Trust Which Teacher for Weakly Supervised ASR","display_name":"Learning When to Trust Which Teacher for Weakly Supervised ASR","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822844","doi":"https://doi.org/10.21437/interspeech.2023-2205"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-2205","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-2205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5012625793","display_name":"Aakriti Agrawal","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aakriti Agrawal","raw_affiliation_strings":["University of Maryland, U.S.A"],"affiliations":[{"raw_affiliation_string":"University of Maryland, U.S.A","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102902212","display_name":"Milind Rao","orcid":"https://orcid.org/0000-0002-6942-7833"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Milind Rao","raw_affiliation_strings":["Amazon Alexa AI, U.S.A"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI, U.S.A","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019965945","display_name":"Anit Kumar Sahu","orcid":"https://orcid.org/0000-0002-4083-0418"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anit Kumar Sahu","raw_affiliation_strings":["Amazon Alexa AI, U.S.A"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI, U.S.A","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063725454","display_name":"Gopinath Chennupati","orcid":"https://orcid.org/0000-0002-6223-8570"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gopinath Chennupati","raw_affiliation_strings":["Amazon Alexa AI, U.S.A"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI, U.S.A","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":["Amazon Alexa AI, U.S.A"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI, U.S.A","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5012625793"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09399793,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"381","last_page":"385"},"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/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"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/T10028","display_name":"Topic Modeling","score":0.9957000017166138,"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":0.7880433797836304},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7073174118995667},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.6207543015480042},{"id":"https://openalex.org/keywords/cadence","display_name":"Cadence","score":0.5904676914215088},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5820581912994385},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.5528959631919861},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49033093452453613},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47749564051628113},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.45802363753318787},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39455127716064453},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06860601902008057}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7880433797836304},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7073174118995667},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.6207543015480042},{"id":"https://openalex.org/C2777125575","wikidata":"https://www.wikidata.org/wiki/Q14088448","display_name":"Cadence","level":2,"score":0.5904676914215088},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5820581912994385},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.5528959631919861},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49033093452453613},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47749564051628113},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.45802363753318787},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39455127716064453},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06860601902008057},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-2205","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-2205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W1904457459","https://openalex.org/W1993660824","https://openalex.org/W2150884987","https://openalex.org/W2187089797","https://openalex.org/W2405078367","https://openalex.org/W2896457183","https://openalex.org/W2966327190","https://openalex.org/W2995181338","https://openalex.org/W3008313712","https://openalex.org/W3045672834","https://openalex.org/W3110846353","https://openalex.org/W3162424266","https://openalex.org/W3198740179","https://openalex.org/W3215427016","https://openalex.org/W4226302796","https://openalex.org/W4286224990","https://openalex.org/W4295116917","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4289538008","https://openalex.org/W3186427148","https://openalex.org/W2138282914","https://openalex.org/W2065850627","https://openalex.org/W2017012638","https://openalex.org/W2071885361","https://openalex.org/W1966793535","https://openalex.org/W1964447062","https://openalex.org/W2088265144","https://openalex.org/W2386641302"],"abstract_inverted_index":{"Automatic":[0],"speech":[1],"recognition":[2],"(ASR)":[3],"training":[4,36,72,76],"can":[5],"utilize":[6],"multiple":[7,68],"experts":[8,70,152],"as":[9],"teacher":[10],"models,":[11],"each":[12],"trained":[13],"on":[14,104],"a":[15,95,146],"specific":[16],"domain":[17,69],"or":[18,34,85,150],"accent.Teacher":[19],"models":[20,49],"may":[21,29],"be":[22,30,32],"opaque":[23],"in":[24,71,81,114],"nature":[25],"since":[26],"their":[27,35],"architecture":[28],"not":[31],"known":[33],"cadence":[37],"is":[38,78],"different":[39],"from":[40,67],"that":[41,91,98,139],"of":[42,121,133],"the":[43,47,54,59,105,111,119,143],"student":[44,48,73,112],"ASR":[45,74],"model.Still,":[46],"are":[50,89],"updated":[51],"incrementally":[52],"using":[53,124,153],"pseudo-labels":[55],"generated":[56],"independently":[57],"by":[58],"expert":[60,102,148],"teachers.In":[61],"this":[62],"paper,":[63],"we":[64,93],"exploit":[65],"supervision":[66],"models.This":[75],"strategy":[77],"especially":[79],"useful":[80],"scenarios":[82],"where":[83],"few":[84],"no":[86],"human":[87],"transcriptions":[88],"available.To":[90],"end,":[92],"propose":[94],"Smart-Weighter":[96],"mechanism":[97],"selects":[99],"an":[100,115,131],"appropriate":[101],"based":[103],"input":[106],"audio,":[107],"and":[108,126,129],"then":[109],"trains":[110],"model":[113],"unsupervised":[116],"setting.We":[117],"show":[118],"efficacy":[120],"our":[122],"approach":[123],"LibriSpeech":[125],"LibriLight":[127],"benchmarks":[128],"find":[130],"improvement":[132],"4":[134],"to":[135],"25%":[136],"over":[137],"baselines":[138],"uniformly":[140],"weight":[141],"all":[142],"experts,":[144],"use":[145],"single":[147],"model,":[149],"combine":[151],"ROVER.":[154]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}