{"id":"https://openalex.org/W4403863362","doi":"https://doi.org/10.1109/lsp.2024.3487795","title":"Unsupervised Domain Adaptation on End-to-End Multi-Talker Overlapped Speech Recognition","display_name":"Unsupervised Domain Adaptation on End-to-End Multi-Talker Overlapped Speech Recognition","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4403863362","doi":"https://doi.org/10.1109/lsp.2024.3487795"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2024.3487795","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3487795","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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":null,"display_name":"Lin Zheng","orcid":"https://orcid.org/0009-0001-1578-4202"},"institutions":[{"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":"Lin Zheng","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-1578-4202","affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Han Zhu","orcid":"https://orcid.org/0009-0002-5060-4454"},"institutions":[{"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":"Han Zhu","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-5060-4454","affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028056375","display_name":"Sanli Tian","orcid":null},"institutions":[{"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":"Sanli Tian","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5560-7673","affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101651591","display_name":"Qingwei Zhao","orcid":"https://orcid.org/0000-0001-9272-2614"},"institutions":[{"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":"Qingwei Zhao","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9272-2614","affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","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/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":"Ta Li","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5431-9787","affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.507,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.83107692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"31","issue":null,"first_page":"3119","last_page":"3123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9729999899864197,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9729999899864197,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9652000069618225,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.825595498085022},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.722507894039154},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7094307541847229},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.569654643535614},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4959283769130707},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41101574897766113},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3866976499557495},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3767915368080139},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11751255393028259},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09585869312286377}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.825595498085022},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.722507894039154},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7094307541847229},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.569654643535614},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4959283769130707},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41101574897766113},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3866976499557495},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3767915368080139},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11751255393028259},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09585869312286377},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2024.3487795","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3487795","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4832241680","display_name":null,"funder_award_id":"2022ZD0116103","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"}],"funders":[{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2115483887","https://openalex.org/W2127141656","https://openalex.org/W2962684181","https://openalex.org/W2962780374","https://openalex.org/W2963242190","https://openalex.org/W3020336359","https://openalex.org/W3094821064","https://openalex.org/W3196117288","https://openalex.org/W3198098585","https://openalex.org/W3207834622","https://openalex.org/W4224925136","https://openalex.org/W4226418945","https://openalex.org/W4297841547","https://openalex.org/W4319990555","https://openalex.org/W4372349800","https://openalex.org/W4385656656","https://openalex.org/W4385822334","https://openalex.org/W4385822384","https://openalex.org/W4386025763","https://openalex.org/W4388017359","https://openalex.org/W4391021006","https://openalex.org/W4391021535","https://openalex.org/W4391021761","https://openalex.org/W4391215800","https://openalex.org/W4392903212","https://openalex.org/W6662227517","https://openalex.org/W6733814495","https://openalex.org/W6741874079","https://openalex.org/W6777776875"],"related_works":["https://openalex.org/W4394775207","https://openalex.org/W4389474468","https://openalex.org/W4300172004","https://openalex.org/W4321649381","https://openalex.org/W2997645659","https://openalex.org/W3180787869","https://openalex.org/W3203792196","https://openalex.org/W2955455867","https://openalex.org/W4295929828","https://openalex.org/W3156096827"],"abstract_inverted_index":{"Serialized":[0],"Output":[1],"Training":[2],"(SOT)":[3],"has":[4],"emerged":[5],"as":[6,195,203],"the":[7,12,39,87,111,126,142,171],"mainstream":[8],"approach":[9],"for":[10,66],"addressing":[11],"multi-talker":[13],"overlapped":[14],"speech":[15],"recognition":[16],"challenge":[17],"due":[18],"to":[19,85,109,165],"its":[20,30],"simplicity.":[21],"However,":[22],"SOT":[23,64],"encounters":[24],"cross-domain":[25],"performance":[26],"degradation":[27],"which":[28,49],"hinders":[29],"application.":[31],"Meanwhile,":[32],"traditional":[33],"domain":[34,67,197],"adaption":[35],"methods":[36],"may":[37],"harm":[38],"accuracy":[40,88],"of":[41,89,113,129,141,157,191],"speaker":[42,71,90],"change":[43,72,91],"point":[44,92],"prediction":[45],"evaluated":[46],"by":[47,69,99],"UD-CER,":[48],"is":[50],"an":[51],"important":[52],"metric":[53],"in":[54],"SOT.":[55],"To":[56],"solve":[57],"these":[58],"issues,":[59],"we":[60,95,145],"propose":[61],"Pseudo-Labeling":[62],"based":[63],"(PL-SOT)":[65],"adaptation":[68],"treating":[70],"token":[73],"(<inline-formula":[74],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[75,79,102,118,121,131,135,148,159,162,173,177],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[76,80,119,122,132,136,160,163,174,178],"notation=\"LaTeX\">$&lt;":[77,133,175],"$</tex-math></inline-formula>sc<inline-formula":[78,134,176],"notation=\"LaTeX\">$&gt;$</tex-math></inline-formula>)":[81],"specially":[82],"during":[83],"training":[84],"increase":[86],"prediction.":[93,180],"Firstly,":[94],"improve":[96],"CTC":[97],"loss":[98,108],"proposing":[100],"<italic":[101,147],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Weakening":[103],"and":[104,198],"Enhancing":[105],"CTC</i>":[106],"(WE-CTC)":[107],"weaken":[110],"learning":[112],"error-prone":[114],"labels":[115],"surrounding":[116],"<inline-formula":[117,130,158,172],"notation=\"LaTeX\">$&lt;$</tex-math></inline-formula>sc<inline-formula":[120,161],"notation=\"LaTeX\">$&gt;$</tex-math></inline-formula>":[123,137,164,179],"while":[124],"enhance":[125],"emission":[127],"probability":[128],"through":[138],"modifying":[139],"posteriors":[140],"pseudo-labels.":[143],"Secondly,":[144],"introduce":[146],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Weighted":[149],"Confidence":[150],"Filter</i>":[151],"(WCF)":[152],"that":[153,184],"assigns":[154],"higher":[155],"scores":[156],"exclude":[166],"low-quality":[167],"pseudo-labels":[168],"without":[169],"hurting":[170],"Experimental":[181],"results":[182],"show":[183],"PL-SOT":[185],"achieves":[186],"17.7%/12.8%":[187],"average":[188],"relative":[189],"reduction":[190],"CER/UD-CER,":[192],"with":[193,201],"AliMeeting":[194],"source":[196],"AISHELL-4":[199],"along":[200],"MagicData-RAMC":[202],"target":[204],"domain.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}