{"id":"https://openalex.org/W4293518994","doi":"https://doi.org/10.1109/icme52920.2022.9859822","title":"An Experimental Comparison between Low-Resource Semi-Supervised and High-Resource Supervised Automatic Speech Recognition Models","display_name":"An Experimental Comparison between Low-Resource Semi-Supervised and High-Resource Supervised Automatic Speech Recognition Models","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4293518994","doi":"https://doi.org/10.1109/icme52920.2022.9859822"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9859822","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859822","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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 Multimedia and Expo (ICME)","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/A5088973051","display_name":"Aoran Gan","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ao-Ran Gan","raw_affiliation_strings":["NEL-SLIP, University of Science and Technology of China (USTC),Hefei,China","NEL-SLIP, University of Science and Technology of China (USTC), Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEL-SLIP, University of Science and Technology of China (USTC),Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NEL-SLIP, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436848","display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0003-1124-0854"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhang","raw_affiliation_strings":["NEL-SLIP, University of Science and Technology of China (USTC),Hefei,China","State Key Laboratory of Acoustics, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","NEL-SLIP, University of Science and Technology of China (USTC), Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEL-SLIP, University of Science and Technology of China (USTC),Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"State Key Laboratory of Acoustics, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"raw_affiliation_string":"NEL-SLIP, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101925641","display_name":"Minghui Wu","orcid":"https://orcid.org/0000-0001-8179-7119"},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming-Hui Wu","raw_affiliation_strings":["iFlytek Research, iFlytek Co., Ltd.,Hefei,China","iFlytek Research, iFlytek Co., Ltd., Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFlytek Research, iFlytek Co., Ltd.,Hefei,China","institution_ids":["https://openalex.org/I173632517"]},{"raw_affiliation_string":"iFlytek Research, iFlytek Co., Ltd., Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101716884","display_name":"Xin Fang","orcid":"https://orcid.org/0000-0003-4796-9444"},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Fang","raw_affiliation_strings":["iFlytek Research, iFlytek Co., Ltd.,Hefei,China","iFlytek Research, iFlytek Co., Ltd., Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFlytek Research, iFlytek Co., Ltd.,Hefei,China","institution_ids":["https://openalex.org/I173632517"]},{"raw_affiliation_string":"iFlytek Research, iFlytek Co., Ltd., Hefei, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Rong Dai","raw_affiliation_strings":["NEL-SLIP, University of Science and Technology of China (USTC),Hefei,China","NEL-SLIP, University of Science and Technology of China (USTC), Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEL-SLIP, University of Science and Technology of China (USTC),Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NEL-SLIP, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9993000030517578,"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":0.998199999332428,"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":0.7419862747192383},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.6157927513122559},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.6105582118034363},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5961078405380249},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.5543894171714783},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5400477647781372},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5311922430992126},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5168941020965576},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4384933114051819},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.09373608231544495},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07487428188323975}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7419862747192383},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.6157927513122559},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.6105582118034363},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5961078405380249},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.5543894171714783},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5400477647781372},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5311922430992126},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5168941020965576},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4384933114051819},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.09373608231544495},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07487428188323975},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme52920.2022.9859822","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859822","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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 Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.46000000834465027}],"awards":[{"id":"https://openalex.org/G634576251","display_name":null,"funder_award_id":"62101523","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8603829020","display_name":null,"funder_award_id":"XDC08010200","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2013598660","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2160815625","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2941814890","https://openalex.org/W2951974815","https://openalex.org/W2953070460","https://openalex.org/W2963250244","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W2995181338","https://openalex.org/W3015522062","https://openalex.org/W3026041220","https://openalex.org/W3035160371","https://openalex.org/W3035202887","https://openalex.org/W3036601975","https://openalex.org/W3093579165","https://openalex.org/W3097777922","https://openalex.org/W3160525311","https://openalex.org/W3197223534","https://openalex.org/W3198098585","https://openalex.org/W4297808394","https://openalex.org/W6733814495","https://openalex.org/W6761563299","https://openalex.org/W6769196770","https://openalex.org/W6780218876","https://openalex.org/W6784436999","https://openalex.org/W6784614252","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W4312414840","https://openalex.org/W2794908468","https://openalex.org/W4206276646","https://openalex.org/W2943467239","https://openalex.org/W1571801203","https://openalex.org/W101422005","https://openalex.org/W192740413","https://openalex.org/W3004135598","https://openalex.org/W2952937263","https://openalex.org/W2131153761"],"abstract_inverted_index":{"Automatic":[0],"speech":[1],"recognition":[2],"(ASR)":[3],"is":[4,38,49,108],"an":[5,78,118],"important":[6],"module":[7],"in":[8,95,117,158],"many":[9],"multimedia":[10],"applications.":[11],"Recently,":[12],"semi-supervised":[13,56,130,155],"ASR":[14,41,156],"has":[15],"attracted":[16],"increasing":[17],"attention,":[18],"which":[19,146],"can":[20,138],"be":[21,148],"classified":[22],"into":[23],"self-supervised":[24,85],"learning":[25,86],"and":[26,90,103],"self-training.":[27],"It":[28],"was":[29],"shown":[30],"that":[31,123],"the":[32,35,55,82,128,143,152],"combination":[33,83],"of":[34,84,154],"two":[36],"methods":[37],"beneficial":[39,150],"for":[40,151],"on":[42,59,81],"open":[43],"datasets,":[44],"e.g.,":[45],"LibriSpeech.":[46],"However,":[47],"it":[48],"still":[50],"not":[51],"completely":[52],"clear":[53],"how":[54],"model":[57,107,132],"behaves":[58],"more":[60],"challenging":[61],"industrial":[62,98,119],"datasets":[63],"compared":[64],"with":[65],"supervised":[66,144],"approaches":[67],"using":[68,133],"high-resource":[69],"labeled":[70,136],"data.":[71],"In":[72],"this":[73],"paper,":[74],"we":[75],"therefore":[76],"present":[77],"experimental":[79],"study":[80],"(e.g.,":[87,92],"wav2vec":[88,105],"2.0)":[89],"self-training":[91],"noisy":[93],"student)":[94],"a":[96,112],"low-resource":[97,159],"setting.":[99,120],"The":[100],"in-domain":[101],"pre-trained":[102],"fine-tuned":[104],"2.0":[106],"utilized":[109],"to":[110],"teach":[111],"baseline":[113],"VGG-Transformer":[114],"by":[115],"pseudo-labeling":[116],"Results":[121],"reveal":[122],"without":[124],"extra":[125],"language":[126],"models":[127,157],"combined":[129],"acoustic":[131],"much":[134],"less":[135],"data":[137],"perform":[139],"as":[140,142],"well":[141],"counterpart,":[145],"would":[147],"rather":[149],"application":[153],"scenarios.":[160]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}