{"id":"https://openalex.org/W2972787773","doi":"https://doi.org/10.1109/access.2019.2940961","title":"Large-Scale Semi-Supervised Training in Deep Learning Acoustic Model for ASR","display_name":"Large-Scale Semi-Supervised Training in Deep Learning Acoustic Model for ASR","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2972787773","doi":"https://doi.org/10.1109/access.2019.2940961","mag":"2972787773"},"language":"en","primary_location":{"id":"doi:10.1109/access.2019.2940961","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2940961","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08835895.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08835895.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056415893","display_name":"Yanhua Long","orcid":"https://orcid.org/0000-0003-0924-408X"},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yanhua Long","raw_affiliation_strings":["SHNU-Unisound Joint Laboratory of Natural Human-Computer Interaction, Shanghai Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0924-408X","affiliations":[{"raw_affiliation_string":"SHNU-Unisound Joint Laboratory of Natural Human-Computer Interaction, Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039983089","display_name":"Yijie Li","orcid":"https://orcid.org/0009-0004-3636-9624"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yijie Li","raw_affiliation_strings":["Beijing Unisound Information Technology Company Ltd., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Unisound Information Technology Company Ltd., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101917656","display_name":"Shuang Wei","orcid":"https://orcid.org/0000-0002-6250-6926"},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuang Wei","raw_affiliation_strings":["SHNU-Unisound Joint Laboratory of Natural Human-Computer Interaction, Shanghai Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SHNU-Unisound Joint Laboratory of Natural Human-Computer Interaction, Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018064730","display_name":"Qiaozheng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiaozheng Zhang","raw_affiliation_strings":["SHNU-Unisound Joint Laboratory of Natural Human-Computer Interaction, Shanghai Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SHNU-Unisound Joint Laboratory of Natural Human-Computer Interaction, Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101774373","display_name":"Chunxia Yang","orcid":"https://orcid.org/0000-0003-2445-8692"},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunxia Yang","raw_affiliation_strings":["SHNU-Unisound Joint Laboratory of Natural Human-Computer Interaction, Shanghai Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SHNU-Unisound Joint Laboratory of Natural Human-Computer Interaction, Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5056415893"],"corresponding_institution_ids":["https://openalex.org/I21945476"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.3066,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.85822331,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"7","issue":null,"first_page":"133615","last_page":"133627"},"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":0.9987999796867371,"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/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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/computer-science","display_name":"Computer science","score":0.7914059162139893},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5295062065124512},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5100355744361877},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5087729096412659},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5055334568023682},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4547703266143799},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.43406885862350464},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4293982982635498},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4220300316810608},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3595077395439148},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34197232127189636},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.19708383083343506}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7914059162139893},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5295062065124512},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5100355744361877},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5087729096412659},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5055334568023682},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4547703266143799},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.43406885862350464},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4293982982635498},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4220300316810608},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3595077395439148},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34197232127189636},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.19708383083343506},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2019.2940961","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2940961","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08835895.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:edaabef80cd04ce49e330cae90d977a9","is_oa":true,"landing_page_url":"https://doaj.org/article/edaabef80cd04ce49e330cae90d977a9","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 7, Pp 133615-133627 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2019.2940961","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2940961","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08835895.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6499999761581421}],"awards":[{"id":"https://openalex.org/G7376540038","display_name":null,"funder_award_id":"61701306","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2972787773.pdf","grobid_xml":"https://content.openalex.org/works/W2972787773.grobid-xml"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W330298975","https://openalex.org/W1495749136","https://openalex.org/W1499864241","https://openalex.org/W1877570817","https://openalex.org/W1912128066","https://openalex.org/W1934041838","https://openalex.org/W1975113979","https://openalex.org/W1975954951","https://openalex.org/W1987563958","https://openalex.org/W1993721840","https://openalex.org/W2002342963","https://openalex.org/W2033256038","https://openalex.org/W2056786202","https://openalex.org/W2095629250","https://openalex.org/W2110073835","https://openalex.org/W2124558353","https://openalex.org/W2127499922","https://openalex.org/W2128678390","https://openalex.org/W2143577772","https://openalex.org/W2160815625","https://openalex.org/W2181607856","https://openalex.org/W2189391786","https://openalex.org/W2193413348","https://openalex.org/W2286443923","https://openalex.org/W2293634267","https://openalex.org/W2394932179","https://openalex.org/W2397947827","https://openalex.org/W2404172366","https://openalex.org/W2507595414","https://openalex.org/W2510349098","https://openalex.org/W2512655038","https://openalex.org/W2514608284","https://openalex.org/W2514741789","https://openalex.org/W2515439472","https://openalex.org/W2515753980","https://openalex.org/W2564784249","https://openalex.org/W2667408400","https://openalex.org/W2729190387","https://openalex.org/W2742223267","https://openalex.org/W2747135936","https://openalex.org/W2749475572","https://openalex.org/W2802248956","https://openalex.org/W2889213362","https://openalex.org/W2903158431","https://openalex.org/W2919115771","https://openalex.org/W2935875038","https://openalex.org/W2938947737","https://openalex.org/W2963931415","https://openalex.org/W4230030242","https://openalex.org/W6603931906","https://openalex.org/W6629638798","https://openalex.org/W6629930100","https://openalex.org/W6639808567","https://openalex.org/W6679227803","https://openalex.org/W6687566353","https://openalex.org/W6695606915","https://openalex.org/W6696934422","https://openalex.org/W6712816420","https://openalex.org/W6731251927","https://openalex.org/W6756615331"],"related_works":["https://openalex.org/W4307784074","https://openalex.org/W2309273277","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W2028097510","https://openalex.org/W113247760","https://openalex.org/W2505877856","https://openalex.org/W1967477266","https://openalex.org/W2547793174","https://openalex.org/W2070212102"],"abstract_inverted_index":{"This":[0],"study":[1],"investigated":[2],"large-scale":[3,36,81,155,211],"semi-supervised":[4],"training":[5,58],"(SST)":[6],"to":[7,48,113,205],"improve":[8,206],"acoustic":[9,44,242],"models":[10],"for":[11,108,154],"automatic":[12,50,106,126],"speech":[13],"recognition.":[14],"The":[15,35,213],"conventional":[16],"self-training,":[17],"the":[18,28,49,53,57,77,88,105,125,135,143,150,172,177,185,189,207,218,221,240],"recently":[19],"proposed":[20,195,222],"committee-based":[21],"SST":[22,30,37,78,219],"using":[23],"heterogeneous":[24],"neural":[25,42],"networks":[26],"and":[27,33,61,123,140,157,184],"lattice-based":[29],"were":[31],"examined":[32],"compared.":[34],"was":[38,84,245],"studied":[39],"in":[40,104,163,210],"deep":[41],"network":[43],"modeling":[45],"with":[46,118,220,239],"respect":[47],"transcription":[51,107,138],"quality,":[52],"importance":[54,141],"data":[55,59,63,96,145,152,179,183,186,208,223],"filtering,":[56],"quantity":[60,68,153],"other":[62],"attributes":[64,180],"of":[65,69,102,132,142,181,188],"a":[66,99,129,196,226,250],"large":[67,161],"multi-genre":[70,235],"unsupervised":[71,120,182],"live":[72],"data.":[73],"We":[74],"found":[75],"that":[76,171,217,244],"behavior":[79,89],"on":[80,91,166,176,202,233,249],"ASR":[82,191],"tasks":[83],"very":[85],"different":[86,167],"from":[87],"obtained":[90],"small-scale":[92],"SST:":[93],"1)":[94],"big":[95],"can":[97],"tolerate":[98],"certain":[100,130],"degree":[101,131],"mislabeling":[103],"SST.":[109,212],"It":[110],"is":[111],"possible":[112],"achieve":[114],"further":[115],"performance":[116,164],"gains":[117,165],"more":[119,147],"fresh":[121,144],"data,":[122],"even":[124,238],"transcriptions":[127],"have":[128],"errors;":[133],"2)":[134],"audio":[136],"attributes,":[137],"quality":[139],"are":[146,160],"important":[148],"than":[149],"increased":[151],"SST;":[156],"3)":[158],"there":[159],"differences":[162],"recognition":[168,236],"tasks,":[169,237],"such":[170],"benefits":[173],"highly":[174],"depend":[175],"selected":[178],"scale":[187],"baseline":[190,241],"system.":[192],"Furthermore,":[193],"we":[194],"novel":[197],"utterance":[198],"filtering":[199,224],"approach":[200],"based":[201],"active":[203],"learning":[204],"selection":[209],"experimental":[214],"results":[215],"showed":[216],"yields":[225],"2-11%":[227],"relative":[228],"word":[229],"error":[230],"rate":[231],"reduction":[232],"five":[234],"model":[243],"already":[246],"well":[247],"trained":[248],"10000-hr":[251],"supervised":[252],"dataset.":[253]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}