{"id":"https://openalex.org/W4408352929","doi":"https://doi.org/10.1109/icassp49660.2025.10890841","title":"Hybrid Pseudo-Labeling for Semi-Supervised Automatic Speech Recognition","display_name":"Hybrid Pseudo-Labeling for Semi-Supervised Automatic Speech Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352929","doi":"https://doi.org/10.1109/icassp49660.2025.10890841"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5067997634","display_name":"Zheng Lin","orcid":"https://orcid.org/0000-0002-8432-1658"},"institutions":[{"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":"Lin Zheng","raw_affiliation_strings":["Institute of Acoustics, CAS,Key Lab of Speech Acoustics and Content Understanding,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, CAS,Key Lab of Speech Acoustics and Content Understanding,China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101557449","display_name":"Han Zhu","orcid":"https://orcid.org/0009-0002-5060-4454"},"institutions":[{"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":"Han Zhu","raw_affiliation_strings":["Institute of Acoustics, CAS,Key Lab of Speech Acoustics and Content Understanding,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, CAS,Key Lab of Speech Acoustics and Content Understanding,China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107601103","display_name":"Chengxu Yang","orcid":null},"institutions":[{"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":"Chengxu Yang","raw_affiliation_strings":["Institute of Acoustics, CAS,Key Lab of Speech Acoustics and Content Understanding,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, CAS,Key Lab of Speech Acoustics and Content Understanding,China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451341","display_name":"Xuyang Wang","orcid":"https://orcid.org/0000-0003-0055-0929"},"institutions":[{"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":"Xuyang Wang","raw_affiliation_strings":["Institute of Acoustics, CAS,Key Lab of Speech Acoustics and Content Understanding,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, CAS,Key Lab of Speech Acoustics and Content Understanding,China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072887461","display_name":"Gaofeng Cheng","orcid":"https://orcid.org/0000-0002-2102-6061"},"institutions":[{"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":"Gaofeng Cheng","raw_affiliation_strings":["Institute of Acoustics, CAS,Key Lab of Speech Acoustics and Content Understanding,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, CAS,Key Lab of Speech Acoustics and Content Understanding,China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052454197","display_name":"Li Ta","orcid":"https://orcid.org/0000-0001-5431-9787"},"institutions":[{"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":"Ta Li","raw_affiliation_strings":["Institute of Acoustics, CAS,Key Lab of Speech Acoustics and Content Understanding,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, CAS,Key Lab of Speech Acoustics and Content Understanding,China","institution_ids":["https://openalex.org/I4210099069"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210099069"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9451000094413757,"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":0.9451000094413757,"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":0.9117000102996826,"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":0.7654005885124207},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7012675404548645},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48342645168304443},{"id":"https://openalex.org/keywords/semi-automatic","display_name":"Semi automatic","score":0.4683225750923157},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4194064140319824},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3964829742908478},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3854178190231323},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34458237886428833},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09394851326942444}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7654005885124207},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7012675404548645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48342645168304443},{"id":"https://openalex.org/C3017741341","wikidata":"https://www.wikidata.org/wiki/Q1047852","display_name":"Semi automatic","level":2,"score":0.4683225750923157},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4194064140319824},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3964829742908478},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3854178190231323},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34458237886428833},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09394851326942444},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2407080277","https://openalex.org/W2766219058","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2963242190","https://openalex.org/W3015457435","https://openalex.org/W3018242354","https://openalex.org/W3096338464","https://openalex.org/W3163464943","https://openalex.org/W3163724562","https://openalex.org/W3198098585","https://openalex.org/W4212772209","https://openalex.org/W4284974905","https://openalex.org/W4285203343","https://openalex.org/W4372349800","https://openalex.org/W4385656656","https://openalex.org/W4385822384","https://openalex.org/W4386025763","https://openalex.org/W4388017359","https://openalex.org/W4402167588","https://openalex.org/W4403863362","https://openalex.org/W4408352078","https://openalex.org/W6691509046","https://openalex.org/W6733814495","https://openalex.org/W6771467084"],"related_works":["https://openalex.org/W191108438","https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W249088392","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2559837139","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Pseudo-labeling":[0],"based":[1,56],"semi-supervised":[2],"learning":[3],"can":[4],"mitigate":[5],"the":[6,11,17,22,29,36,45,46,67,80,88,121],"performance":[7,134],"degradation":[8],"resulting":[9],"from":[10,87],"absence":[12],"of":[13,24,39,69,107,123],"labeled":[14],"data":[15],"in":[16,93],"target":[18],"domain.":[19],"In":[20],"pseudo-labeling,":[21],"quality":[23,68,122],"pseudo-labels":[25,43,70,124],"is":[26],"crucial":[27],"for":[28,42,95],"final":[30],"performance.":[31],"However,":[32],"most":[33],"works":[34],"overlook":[35],"potential":[37],"benefits":[38],"using":[40,79],"decoder":[41,81],"within":[44],"mainstream":[47,138],"hybrid":[48],"Connectionist":[49],"Temporal":[50],"Classification":[51],"(CTC)":[52],"and":[53,109],"attention":[54],"(CTC/attention)":[55],"ASR":[57],"architecture.":[58],"Therefore,":[59],"we":[60,99,112],"propose":[61,100],"Hybrid":[62,101],"Pseudo-Labeling":[63],"(HPL)":[64],"to":[65,82,103,118,136],"improve":[66],"during":[71],"online":[72],"decoding.":[73],"HPL":[74,131],"introduces":[75],"a":[76],"second-stage":[77],"decoding":[78],"alleviate":[83],"substitution":[84],"errors":[85],"arising":[86],"conditional":[89],"independence":[90],"assumption":[91],"inherent":[92],"CTC":[94],"error":[96],"correction.":[97],"Furthermore,":[98],"Selection":[102],"optimally":[104],"combine":[105],"results":[106],"encoder":[108],"decoder.":[110],"Additionally,":[111],"introduce":[113],"Speed":[114],"Perturbation":[115],"Enhancement":[116],"(SPE)":[117],"further":[119],"enhance":[120],"via":[125],"speed":[126],"perturbation.":[127],"Experiments":[128],"demonstrate":[129],"that":[130],"achieves":[132],"state-of-the-art":[133],"compared":[135],"other":[137],"pseudo-labeling":[139],"methods.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
