{"id":"https://openalex.org/W4386591026","doi":"https://doi.org/10.1109/taslp.2023.3313434","title":"A Semi-Supervised Complementary Joint Training Approach for Low-Resource Speech Recognition","display_name":"A Semi-Supervised Complementary Joint Training Approach for Low-Resource Speech Recognition","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386591026","doi":"https://doi.org/10.1109/taslp.2023.3313434"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3313434","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3313434","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5026915452","display_name":"Yeqian Du","orcid":"https://orcid.org/0000-0002-6176-8676"},"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":"Ye-Qian Du","raw_affiliation_strings":["School of Data Science, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0002-6176-8676","affiliations":[{"raw_affiliation_string":"School of Data Science, University of Science and Technology of China, Hefei, Anhui, 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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhang","raw_affiliation_strings":["Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-1124-0854","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101814613","display_name":"Xin Fang","orcid":"https://orcid.org/0009-0001-6003-9439"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Fang","raw_affiliation_strings":["iFlytek Research, Hefei, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFlytek Research, Hefei, Anhui, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101925641","display_name":"Minghui Wu","orcid":"https://orcid.org/0000-0001-8179-7119"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming-Hui Wu","raw_affiliation_strings":["iFlytek Research, Hefei, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFlytek Research, Hefei, Anhui, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047580521","display_name":"Zhouwang Yang","orcid":"https://orcid.org/0000-0002-9454-9146"},"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":"Zhou-Wang Yang","raw_affiliation_strings":["School of Mathematical Sciences, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0002-9454-9146","affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2208,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.89793246,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"3908","last_page":"3921"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9957000017166138,"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/T11309","display_name":"Music and Audio Processing","score":0.9941999912261963,"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":0.710521936416626},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.689864993095398},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.6032931208610535},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5862832069396973},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4617682993412018},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4529194235801697},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43139633536338806},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42771580815315247},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38621193170547485}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.710521936416626},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.689864993095398},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.6032931208610535},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5862832069396973},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4617682993412018},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4529194235801697},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43139633536338806},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42771580815315247},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38621193170547485},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"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/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3313434","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3313434","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"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"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":103,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1647671624","https://openalex.org/W1828163288","https://openalex.org/W2037034710","https://openalex.org/W2124558353","https://openalex.org/W2127141656","https://openalex.org/W2219249508","https://openalex.org/W2327501763","https://openalex.org/W2400208341","https://openalex.org/W2404126548","https://openalex.org/W2512655038","https://openalex.org/W2577366047","https://openalex.org/W2587275078","https://openalex.org/W2748795451","https://openalex.org/W2802248956","https://openalex.org/W2808640845","https://openalex.org/W2842511635","https://openalex.org/W2883586237","https://openalex.org/W2889213362","https://openalex.org/W2892009249","https://openalex.org/W2896457183","https://openalex.org/W2913851961","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2938947737","https://openalex.org/W2940322076","https://openalex.org/W2941814890","https://openalex.org/W2952711665","https://openalex.org/W2962699523","https://openalex.org/W2963240019","https://openalex.org/W2963925437","https://openalex.org/W2964012862","https://openalex.org/W2972889948","https://openalex.org/W2972943112","https://openalex.org/W2972981541","https://openalex.org/W2972991710","https://openalex.org/W2982095018","https://openalex.org/W2988736778","https://openalex.org/W2990391581","https://openalex.org/W2990906560","https://openalex.org/W2995181338","https://openalex.org/W2998532468","https://openalex.org/W3000915284","https://openalex.org/W3015208154","https://openalex.org/W3015237657","https://openalex.org/W3015280134","https://openalex.org/W3015522062","https://openalex.org/W3033411150","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3092028330","https://openalex.org/W3095350795","https://openalex.org/W3096273170","https://openalex.org/W3096297644","https://openalex.org/W3096338464","https://openalex.org/W3096485810","https://openalex.org/W3097647528","https://openalex.org/W3097777922","https://openalex.org/W3112034174","https://openalex.org/W3113594615","https://openalex.org/W3122931219","https://openalex.org/W3141100132","https://openalex.org/W3155427814","https://openalex.org/W3160525311","https://openalex.org/W3161143478","https://openalex.org/W3163464943","https://openalex.org/W3163605596","https://openalex.org/W3197223534","https://openalex.org/W3198836239","https://openalex.org/W3200601846","https://openalex.org/W3205080563","https://openalex.org/W3205644108","https://openalex.org/W3208049241","https://openalex.org/W3209059054","https://openalex.org/W4210690962","https://openalex.org/W4210758944","https://openalex.org/W4224902998","https://openalex.org/W4285144981","https://openalex.org/W4287173589","https://openalex.org/W4294103325","https://openalex.org/W4296068827","https://openalex.org/W4297808394","https://openalex.org/W4319862269","https://openalex.org/W6636915900","https://openalex.org/W6656414902","https://openalex.org/W6688816777","https://openalex.org/W6752630080","https://openalex.org/W6752726010","https://openalex.org/W6761563299","https://openalex.org/W6762242920","https://openalex.org/W6769365793","https://openalex.org/W6770514103","https://openalex.org/W6770528390","https://openalex.org/W6772883055","https://openalex.org/W6773139635","https://openalex.org/W6778823374","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6784436999","https://openalex.org/W6786669483","https://openalex.org/W6787141514","https://openalex.org/W6795952400","https://openalex.org/W6810327252"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W3081694532","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611"],"abstract_inverted_index":{"Both":[0],"unpaired":[1,45],"speech":[2,13,46],"and":[3,25,47,85,88,96,118,184],"text":[4,48],"have":[5],"shown":[6],"to":[7,49,71,76,129,148],"be":[8],"beneficial":[9],"for":[10,22,33,116,121,127,160],"low-resource":[11,195],"automatic":[12],"recognition":[14],"(ASR),":[15],"which,":[16],"however":[17],"were":[18],"either":[19],"separately":[20],"used":[21,32,57],"pre-training,":[23],"self-training":[24],"language":[26],"model":[27,72,79],"(LM)":[28],"training,":[29],"or":[30],"jointly":[31],"designing":[34],"hybrid":[35],"models":[36,189],"in":[37,58,69,93,193],"literature.":[38],"In":[39,141],"this":[40],"work,":[41],"we":[42],"leverage":[43],"both":[44,94],"train":[50,77],"a":[51,78],"general":[52],"ASR":[53,165],"model,":[54],"which":[55],"are":[56,124],"the":[59,66,82,90,111,133,143,149,161,172,185],"form":[60],"of":[61,163,174],"data":[62,154],"pairs":[63,87],"by":[64,155],"generating":[65],"missing":[67],"parts":[68],"prior":[70],"training.":[73],"We":[74],"propose":[75],"alternatively":[80],"using":[81],"prepared":[83],"speech-PseudoLabel":[84],"SynthesizedAudio-text":[86],"reveal":[89],"complementary":[91,105],"property":[92],"acoustic":[95],"linguistic":[97],"features.":[98],"The":[99],"proposed":[100,126,144],"method":[101],"is":[102,146,190],"thus":[103],"called":[104],"joint":[106,175],"training":[107,162,176,182],"(CJT).":[108],"Based":[109],"on":[110,169],"basic":[112],"CJT,":[113],"label":[114],"masking":[115],"pseudo-labels":[117],"parallel":[119],"layers":[120],"synthesized":[122],"audio":[123],"then":[125],"re-training":[128],"further":[130],"cope":[131],"with":[132,151],"deviations":[134],"from":[135],"real":[136],"data,":[137],"termed":[138],"as":[139,177,179],"CJT++.":[140],"addition,":[142],"CJT":[145,159],"extended":[147],"scenario":[150],"zero":[152],"paired":[153],"considering":[156],"an":[157],"iterative":[158],"seed":[164],"model.":[166],"Experimental":[167],"results":[168],"Libri-light":[170],"show":[171],"efficacy":[173],"well":[178],"two":[180],"second-round":[181],"strategies,":[183],"superiority":[186],"over":[187],"recent":[188],"validated,":[191],"particularly":[192],"extreme":[194],"cases.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}