{"id":"https://openalex.org/W4289829953","doi":"https://doi.org/10.1109/spcom55316.2022.9840763","title":"Noisy Student Teacher Training with Self Supervised Learning for Children ASR","display_name":"Noisy Student Teacher Training with Self Supervised Learning for Children ASR","publication_year":2022,"publication_date":"2022-07-11","ids":{"openalex":"https://openalex.org/W4289829953","doi":"https://doi.org/10.1109/spcom55316.2022.9840763"},"language":"en","primary_location":{"id":"doi:10.1109/spcom55316.2022.9840763","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom55316.2022.9840763","pdf_url":null,"source":{"id":"https://openalex.org/S4363608579","display_name":"2022 IEEE International Conference on Signal Processing and Communications (SPCOM)","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":"2022 IEEE International Conference on Signal Processing and Communications (SPCOM)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103987250","display_name":"Shreya S. Chaturvedi","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shreya S. Chaturvedi","raw_affiliation_strings":["DA-IICT,Speech Research Lab,Gandhinagar","Speech Research Lab, DA-IICT, Gandhinagar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DA-IICT,Speech Research Lab,Gandhinagar","institution_ids":["https://openalex.org/I98389781"]},{"raw_affiliation_string":"Speech Research Lab, DA-IICT, Gandhinagar","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030912143","display_name":"Hardik B. Sailor","orcid":"https://orcid.org/0000-0001-6872-5153"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hardik B. Sailor","raw_affiliation_strings":["Institute for Infocomm Research (I2R), A*STAR,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R), A*STAR,Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043002276","display_name":"Hemant A. Patil","orcid":"https://orcid.org/0000-0002-4068-2005"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemant A. Patil","raw_affiliation_strings":["DA-IICT,Speech Research Lab,Gandhinagar","Speech Research Lab, DA-IICT, Gandhinagar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DA-IICT,Speech Research Lab,Gandhinagar","institution_ids":["https://openalex.org/I98389781"]},{"raw_affiliation_string":"Speech Research Lab, DA-IICT, Gandhinagar","institution_ids":["https://openalex.org/I98389781"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3374,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54035671,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9945999979972839,"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/T12031","display_name":"Speech and dialogue systems","score":0.9945999979972839,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9944999814033508,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9577999711036682,"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":0.7864620685577393},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5892661213874817},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5816774368286133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5110515356063843},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.4649907946586609},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.45472991466522217},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4269932508468628},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3840716481208801},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33236122131347656},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2780821621417999},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08974215388298035}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7864620685577393},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5892661213874817},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5816774368286133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5110515356063843},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.4649907946586609},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.45472991466522217},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4269932508468628},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3840716481208801},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33236122131347656},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2780821621417999},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08974215388298035},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/spcom55316.2022.9840763","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom55316.2022.9840763","pdf_url":null,"source":{"id":"https://openalex.org/S4363608579","display_name":"2022 IEEE International Conference on Signal Processing and Communications (SPCOM)","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":"2022 IEEE International Conference on Signal Processing and Communications (SPCOM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1761388607","https://openalex.org/W1997922073","https://openalex.org/W350032239","https://openalex.org/W2604685715","https://openalex.org/W2412160900","https://openalex.org/W2136453575","https://openalex.org/W1596913645","https://openalex.org/W1024498263"],"abstract_inverted_index":{"Automatic":[0],"Speech":[1],"Recognition":[2],"(ASR)":[3],"is":[4,27,67,77,92,136,143,228],"a":[5,133,144],"fast-growing":[6],"field,":[7],"where":[8],"reliable":[9],"systems":[10],"are":[11,174],"made":[12],"for":[13,18,29,59,167],"high":[14],"resource":[15],"languages":[16],"and":[17,40,148,158,182,187,223],"adult\u2019s":[19],"speech.":[20,63],"However,":[21],"performance":[22,76,210,221],"of":[23,42,83,100,106,114,125,180,185,209,220,225],"such":[24],"ASR":[25,57,70,152],"system":[26,58],"inefficient":[28],"children":[30,38,62],"speech,":[31],"due":[32],"to":[33,49,55,96,170],"numerous":[34],"acoustic":[35],"variability":[36],"in":[37,123,138,146,230],"speech":[39],"scarcity":[41],"resources.":[43],"In":[44,151],"this":[45,139],"paper,":[46,140],"we":[47],"propose":[48],"use":[50,99],"the":[51,68,81,98,112,126,214,218],"unlabeled":[52,107],"data":[53,189],"extensively":[54],"develop":[56],"low":[60],"resourced":[61],"State-of-the-art":[64],"wav2vec":[65,201],"2.0":[66,202],"baseline":[69,200],"technique":[71,91],"used":[72,157,166,191],"here.":[73],"The":[74,89,199],"baseline\u2019s":[75],"further":[78],"enhanced":[79],"with":[80,176],"intuition":[82],"Noisy":[84],"Student":[85],"Teacher":[86],"(NST)":[87],"learning.":[88,150],"proposed":[90,215],"not":[93],"only":[94],"limited":[95],"introducing":[97],"soft":[101],"labels":[102],"(i.e.,":[103],"word-level":[104],"transcription)":[105],"data,":[108],"but":[109],"also":[110],"adapts":[111],"learning":[113],"teacher":[115,147],"model":[116,227],"or":[117],"preceding":[118],"student":[119,149],"model,":[120],"which":[121],"results":[122],"reduction":[124],"redundant":[127],"training":[128],"significantly.":[129],"To":[130],"that":[131],"effect,":[132],"detailed":[134],"analysis":[135,219],"reported":[137],"as":[141],"there":[142],"difference":[145],"experiments,":[153],"character-level":[154],"tokenization":[155],"was":[156,165,190,211],"hence,":[159],"Connectionist":[160],"Temporal":[161],"Classification":[162],"(CTC)":[163],"loss":[164,222],"fine-tuning.":[168],"Due":[169],"computational":[171],"limitations,":[172],"experiments":[173],"performed":[175],"approximately":[177],"12":[178],"hours":[179,184],"training,":[181],"5":[183],"development":[186],"test":[188],"from":[192],"standard":[193],"My":[194],"Science":[195],"Tutor":[196],"(MyST)":[197],"corpus.":[198],"achieves":[203],"34%":[204],"WER,":[205],"while":[206],"relatively":[207],"10%":[208],"improved":[212],"using":[213],"approach.":[216],"Further,":[217],"effect":[224],"language":[226],"discussed":[229],"details.":[231]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}