{"id":"https://openalex.org/W3096273170","doi":"https://doi.org/10.21437/interspeech.2020-1337","title":"Semi-Supervised Learning with Data Augmentation for End-to-End ASR","display_name":"Semi-Supervised Learning with Data Augmentation for End-to-End ASR","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096273170","doi":"https://doi.org/10.21437/interspeech.2020-1337","mag":"3096273170"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1337","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1337","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":"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/A5016747567","display_name":"Felix Weninger","orcid":null},"institutions":[{"id":"https://openalex.org/I2799286240","display_name":"Burlington College","ror":"https://ror.org/016j6dw22","country_code":"US","type":"education","lineage":["https://openalex.org/I2799286240"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Felix Weninger","raw_affiliation_strings":["Burlington, MA, USA,"],"affiliations":[{"raw_affiliation_string":"Burlington, MA, USA,","institution_ids":["https://openalex.org/I2799286240"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048085326","display_name":"Franco Mana","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095558","display_name":"5T Torino (Italy)","ror":"https://ror.org/00k7znw93","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210095558"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Franco Mana","raw_affiliation_strings":["Torino, Italy,"],"affiliations":[{"raw_affiliation_string":"Torino, Italy,","institution_ids":["https://openalex.org/I4210095558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056510268","display_name":"Roberto Gemello","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095558","display_name":"5T Torino (Italy)","ror":"https://ror.org/00k7znw93","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210095558"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Roberto Gemello","raw_affiliation_strings":["Torino, Italy,"],"affiliations":[{"raw_affiliation_string":"Torino, Italy,","institution_ids":["https://openalex.org/I4210095558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019869698","display_name":"Jes\u00fas Andr\u00e9s-Ferrer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jes\u00fas Andr\u00e9s-Ferrer","raw_affiliation_strings":["Valencia, Spain"],"affiliations":[{"raw_affiliation_string":"Valencia, Spain","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109588257","display_name":"Puming Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I2799286240","display_name":"Burlington College","ror":"https://ror.org/016j6dw22","country_code":"US","type":"education","lineage":["https://openalex.org/I2799286240"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Puming Zhan","raw_affiliation_strings":["Burlington, MA, USA,"],"affiliations":[{"raw_affiliation_string":"Burlington, MA, USA,","institution_ids":["https://openalex.org/I2799286240"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5016747567"],"corresponding_institution_ids":["https://openalex.org/I2799286240"],"apc_list":null,"apc_paid":null,"fwci":3.4466,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.93893586,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2802","last_page":"2806"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9939000010490417,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.991599977016449,"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":0.7533124685287476},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.7413169741630554},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.7345390319824219},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7003598809242249},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5593532919883728},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5485020279884338},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5462349653244019},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.5173601508140564},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4939597249031067},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.444132924079895},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42645758390426636},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.42288023233413696},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4179580509662628},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.4102252721786499}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7533124685287476},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.7413169741630554},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.7345390319824219},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7003598809242249},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5593532919883728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5485020279884338},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5462349653244019},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.5173601508140564},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4939597249031067},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.444132924079895},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42645758390426636},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.42288023233413696},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4179580509662628},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.4102252721786499},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1337","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1337","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W1975113979","https://openalex.org/W1979651826","https://openalex.org/W2095705004","https://openalex.org/W2133564696","https://openalex.org/W2183341477","https://openalex.org/W2327501763","https://openalex.org/W2407080277","https://openalex.org/W2525778437","https://openalex.org/W2577366047","https://openalex.org/W2750499125","https://openalex.org/W2787812568","https://openalex.org/W2799800213","https://openalex.org/W2889213362","https://openalex.org/W2936774411","https://openalex.org/W2937780860","https://openalex.org/W2938947737","https://openalex.org/W2940322076","https://openalex.org/W2962369866","https://openalex.org/W2962826786","https://openalex.org/W2963827914","https://openalex.org/W2972799770","https://openalex.org/W2972981541","https://openalex.org/W2978426779","https://openalex.org/W2991213871","https://openalex.org/W3001197829","https://openalex.org/W3001770030","https://openalex.org/W3008363190","https://openalex.org/W3015237657","https://openalex.org/W3015265920","https://openalex.org/W3015522062","https://openalex.org/W3015726069","https://openalex.org/W3015737168","https://openalex.org/W3015889230","https://openalex.org/W3035160371","https://openalex.org/W4287902615","https://openalex.org/W4301183790"],"related_works":["https://openalex.org/W2365028544","https://openalex.org/W4309984931","https://openalex.org/W4282977123","https://openalex.org/W2949671220","https://openalex.org/W2013810580","https://openalex.org/W2186210338","https://openalex.org/W4206276646","https://openalex.org/W2371815184","https://openalex.org/W1571801203","https://openalex.org/W4390341236"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,47],"apply":[4],"Semi-Supervised":[5],"Learning":[6],"(SSL)":[7],"along":[8],"with":[9,57,66,78,97,122],"Data":[10],"Augmentation":[11],"(DA)":[12],"for":[13,52],"improving":[14],"the":[15,22,41,49,53,63,109,116,118,172],"accuracy":[16],"of":[17,40,73,108,140,148],"End-to-End":[18],"ASR.We":[19],"focus":[20],"on":[21,89],"consistency":[23,126],"regularization":[24,127],"principle,":[25],"which":[26],"has":[27],"been":[28],"successfully":[29],"applied":[30],"to":[31,76,144,170],"image":[32],"classification":[33],"tasks,":[34],"and":[35,43,125],"present":[36],"sequence-to-sequence":[37],"(seq2seq)":[38],"versions":[39],"FixMatch":[42],"Noisy":[44,119],"Student":[45,120],"algorithms.Specifically,":[46],"generate":[48],"pseudo":[50,79],"labels":[51,111,124],"unlabeled":[54,141,157],"data":[55,93],"onthe-fly":[56],"a":[58,90,145],"seq2seq":[59],"model":[60],"after":[61],"perturbing":[62],"input":[64],"features":[65],"DA.We":[67],"also":[68],"propose":[69],"soft":[70,123],"label":[71,80],"variants":[72],"both":[74],"algorithms":[75],"cope":[77],"errors,":[81],"showing":[82],"further":[83],"performance":[84,162],"improvements.We":[85],"conduct":[86],"SSL":[87,161],"experiments":[88],"conversational":[91],"speech":[92],"set":[94,176],"(doctor-patient":[95],"conversations)":[96],"1.9":[98],"kh":[99],"manually":[100],"transcribed":[101],"training":[102,175],"data,":[103,142,158],"using":[104,171],"only":[105],"25":[106],"%":[107,130,166],"original":[110],"(475":[112],"h":[113,139,155],"labeled":[114,174],"data).In":[115],"result,":[117],"algorithm":[121],"achieves":[128],"10.4":[129],"word":[131],"error":[132],"rate":[133,147],"(WER)":[134],"reduction":[135],"when":[136,151],"adding":[137,153],"475":[138],"corresponding":[143],"recovery":[146],"92":[149],"%.Furthermore,":[150],"iteratively":[152],"950":[154],"more":[156],"our":[159],"best":[160],"is":[163],"within":[164],"5":[165],"WER":[167],"increase":[168],"compared":[169],"full":[173],"(recovery":[177],"rate:":[178],"78":[179],"%).":[180]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":15}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}