{"id":"https://openalex.org/W4317581828","doi":"https://doi.org/10.1186/s13636-023-00273-y","title":"Heterogeneous separation consistency training for adaptation of unsupervised speech separation","display_name":"Heterogeneous separation consistency training for adaptation of unsupervised speech separation","publication_year":2023,"publication_date":"2023-01-20","ids":{"openalex":"https://openalex.org/W4317581828","doi":"https://doi.org/10.1186/s13636-023-00273-y"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-023-00273-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-023-00273-y","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-023-00273-y","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-023-00273-y","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090367911","display_name":"Jiangyu Han","orcid":"https://orcid.org/0000-0001-5390-8520"},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangyu Han","raw_affiliation_strings":["Key Innovation Group of Digital Humanities Resource and Research, Shanghai Normal University, Shanghai, China","Shanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Innovation Group of Digital Humanities Resource and Research, Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]},{"raw_affiliation_string":"Shanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056415893","display_name":"Yanhua Long","orcid":"https://orcid.org/0000-0003-0924-408X"},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yanhua Long","raw_affiliation_strings":["Key Innovation Group of Digital Humanities Resource and Research, Shanghai Normal University, Shanghai, China","Shanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0924-408X","affiliations":[{"raw_affiliation_string":"Key Innovation Group of Digital Humanities Resource and Research, Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]},{"raw_affiliation_string":"Shanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5056415893"],"corresponding_institution_ids":["https://openalex.org/I21945476"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":0.7353,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.67172217,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"2023","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.998199999332428,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973999857902527,"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":0.7581326961517334},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.7101505398750305},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6766535043716431},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.6088050603866577},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5548431277275085},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.47284820675849915},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.4582395553588867},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45662224292755127},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44853973388671875},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.43081581592559814},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34454917907714844}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7581326961517334},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.7101505398750305},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6766535043716431},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.6088050603866577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5548431277275085},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.47284820675849915},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.4582395553588867},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45662224292755127},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44853973388671875},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.43081581592559814},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34454917907714844},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-023-00273-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-023-00273-y","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-023-00273-y","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:8ec6c0c95713493489578d2f43b2a827","is_oa":true,"landing_page_url":"https://doaj.org/article/8ec6c0c95713493489578d2f43b2a827","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2023, Iss 1, Pp 1-17 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-023-00273-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-023-00273-y","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-023-00273-y","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.550000011920929,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G514874842","display_name":"\u4f4e\u8d44\u6e90\u6761\u4ef6\u4e0b\u7684\u91cd\u53e3\u97f3\u9c81\u68d2\u6027\u58f0\u5b66\u5efa\u6a21\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"62071302","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7376540038","display_name":null,"funder_award_id":"61701306","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":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4317581828.pdf"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1901129140","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2291877678","https://openalex.org/W2304609584","https://openalex.org/W2460742184","https://openalex.org/W2510642588","https://openalex.org/W2550143307","https://openalex.org/W2558649592","https://openalex.org/W2560023338","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2891405874","https://openalex.org/W2905258586","https://openalex.org/W2940275453","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2963242190","https://openalex.org/W2963446712","https://openalex.org/W2964058413","https://openalex.org/W2973143779","https://openalex.org/W2988200020","https://openalex.org/W2995166068","https://openalex.org/W3015191643","https://openalex.org/W3015199127","https://openalex.org/W3015654783","https://openalex.org/W3015788098","https://openalex.org/W3015794161","https://openalex.org/W3015843733","https://openalex.org/W3015912787","https://openalex.org/W3016094953","https://openalex.org/W3095219613","https://openalex.org/W3095724876","https://openalex.org/W3096408984","https://openalex.org/W3096893582","https://openalex.org/W3099330747","https://openalex.org/W3124972797","https://openalex.org/W3145364388","https://openalex.org/W3160241658","https://openalex.org/W3163208914","https://openalex.org/W3163346546","https://openalex.org/W3163652268","https://openalex.org/W3168140565","https://openalex.org/W3197103473","https://openalex.org/W3197629192","https://openalex.org/W3206116612","https://openalex.org/W4200634403","https://openalex.org/W4225592424","https://openalex.org/W6600538138","https://openalex.org/W6603242443"],"related_works":["https://openalex.org/W2047973478","https://openalex.org/W4295532600","https://openalex.org/W2071676784","https://openalex.org/W2063823869","https://openalex.org/W2067569035","https://openalex.org/W2090985514","https://openalex.org/W4292513318","https://openalex.org/W2287611352","https://openalex.org/W2021161555","https://openalex.org/W2077498359"],"abstract_inverted_index":{"Abstract":[0],"Recently,":[1],"supervised":[2,15,71],"speech":[3,72,104,144],"separation":[4,19,73,89,105,162,177,204,215,281],"has":[5],"made":[6],"great":[7],"progress.":[8],"However,":[9],"limited":[10],"by":[11,110,217],"the":[12,36,50,57,63,70,96,113,155,171,202,213,226,238,253,260,294,318],"nature":[13],"of":[14,141,245,290],"training,":[16,91],"most":[17],"existing":[18],"methods":[20],"require":[21],"ground-truth":[22,31,37,289],"sources":[23],"and":[24,151,248,259,277,309,320],"are":[25,39,148,197],"trained":[26],"on":[27,272,317],"synthetic":[28],"datasets.":[29,61],"This":[30],"reliance":[32],"is":[33,182,270],"problematic,":[34],"because":[35],"signals":[38],"usually":[40,65],"unavailable":[41],"in":[42,46,59,82,106,241],"real":[43,51,76,143,165,190,261],"conditions.":[44],"Moreover,":[45],"many":[47],"industry":[48],"scenarios,":[49],"acoustic":[52],"characteristics":[53],"deviate":[54],"far":[55],"from":[56,117],"ones":[58],"simulated":[60,187],"Therefore,":[62],"performance":[64],"degrades":[66],"significantly":[67,298],"when":[68],"applying":[69],"models":[74,205],"to":[75,94,135,153,157,200,236,252,306],"applications.":[77],"To":[78,168],"address":[79],"these":[80],"problems,":[81],"this":[83,231],"study,":[84],"we":[85,209,233],"propose":[86],"a":[87,127,179,218],"novel":[88],"consistency":[90],"termed":[92],"SCT,":[93],"exploit":[95],"real-world":[97],"unlabeled":[98,142,262],"mixtures":[99,191],"for":[100,164,256,264],"improving":[101],"cross-domain":[102,239,280,322],"unsupervised":[103],"an":[107],"iterative":[108],"manner,":[109],"leveraging":[111],"upon":[112],"complementary":[114,173],"information":[115,174],"obtained":[116],"heterogeneous":[118,131,214],"(structurally":[119],"distinct":[120],"but":[121],"behaviorally":[122],"complementary)":[123],"models.":[124],"SCT":[125,269,295],"follows":[126],"framework":[128],"using":[129],"two":[130,301],"neural":[132],"networks":[133],"(HNNs)":[134],"produce":[136,158],"high":[137,193],"confidence":[138,194],"pseudo":[139,195],"labels":[140,147,196],"mixtures.":[145],"These":[146],"then":[149,198],"updated":[150],"used":[152,199],"refine":[154],"HNNs":[156],"more":[159],"reliable":[160],"consistent":[161],"results":[163],"mixture":[166,263],"pseudo-labeling.":[167],"maximally":[169],"utilize":[170],"large":[172],"between":[175],"different":[176],"networks,":[178],"cross-knowledge":[180],"adaptation":[181],"further":[183,223],"proposed.":[184],"Together":[185],"with":[186,192,304],"dataset,":[188],"those":[189],"update":[201],"HNN":[203],"iteratively.":[206],"In":[207,230],"addition,":[208],"find":[210],"that":[211],"combing":[212],"outputs":[216],"simple":[219],"linear":[220],"fusion":[221],"can":[222,296],"slightly":[224],"improve":[225],"final":[227],"system":[228],"performance.":[229],"paper,":[232],"use":[234],"cross-dataset":[235],"simulate":[237],"situation":[240],"real-life.":[242],"The":[243,267],"term":[244],"\u201csource":[246],"domain\u201d":[247,250],"\u201ctarget":[249],"refer":[251],"simulation":[254],"set":[255],"model":[257,265],"pre-training":[258],"adaptation.":[266],"proposed":[268],"evaluated":[271],"both":[273],"public":[274],"reverberant":[275],"English":[276,319],"anechoic":[278],"Mandarin":[279,321],"tasks.":[282],"Results":[283],"show":[284],"that,":[285],"without":[286],"any":[287],"available":[288],"target":[291],"domain":[292],"mixtures,":[293],"still":[297],"outperform":[299],"our":[300],"strong":[302],"baselines":[303],"up":[305],"1.61":[307],"dB":[308,311],"3.44":[310],"scale-invariant":[312],"signal-to-noise":[313],"ratio":[314],"(SI-SNR)":[315],"improvements,":[316],"conditions,":[323],"respectively.":[324]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2025-10-10T00:00:00"}