{"id":"https://openalex.org/W4226016254","doi":"https://doi.org/10.1109/taslp.2022.3165712","title":"Dual-Path Modeling With Memory Embedding Model for Continuous Speech Separation","display_name":"Dual-Path Modeling With Memory Embedding Model for Continuous Speech Separation","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4226016254","doi":"https://doi.org/10.1109/taslp.2022.3165712"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3165712","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3165712","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/A5090224430","display_name":"Chenda Li","orcid":"https://orcid.org/0000-0003-0299-9914"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenda Li","raw_affiliation_strings":["X-Lance Lab, Department of Computer Science and Engineering & MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, P. R. China"],"raw_orcid":"https://orcid.org/0000-0003-0299-9914","affiliations":[{"raw_affiliation_string":"X-Lance Lab, Department of Computer Science and Engineering & MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345097","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0003-0563-1760"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["X-Lance Lab, Department of Computer Science and Engineering & MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, P. R. China"],"raw_orcid":"https://orcid.org/0000-0002-0314-3790","affiliations":[{"raw_affiliation_string":"X-Lance Lab, Department of Computer Science and Engineering & MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8484,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.69667078,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"30","issue":null,"first_page":"1508","last_page":"1520"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9991000294685364,"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":0.772177517414093},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7558862566947937},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6533721089363098},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6106317043304443},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.5687573552131653},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5496705770492554},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5388113856315613},{"id":"https://openalex.org/keywords/span","display_name":"Span (engineering)","score":0.5284423828125},{"id":"https://openalex.org/keywords/memory-span","display_name":"Memory span","score":0.49552667140960693},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37092721462249756},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3666003942489624},{"id":"https://openalex.org/keywords/working-memory","display_name":"Working memory","score":0.3171038031578064},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.14955464005470276}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.772177517414093},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7558862566947937},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6533721089363098},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6106317043304443},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.5687573552131653},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5496705770492554},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5388113856315613},{"id":"https://openalex.org/C2778753569","wikidata":"https://www.wikidata.org/wiki/Q1960395","display_name":"Span (engineering)","level":2,"score":0.5284423828125},{"id":"https://openalex.org/C197268465","wikidata":"https://www.wikidata.org/wiki/Q355122","display_name":"Memory span","level":4,"score":0.49552667140960693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37092721462249756},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3666003942489624},{"id":"https://openalex.org/C21963081","wikidata":"https://www.wikidata.org/wiki/Q11337567","display_name":"Working memory","level":3,"score":0.3171038031578064},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.14955464005470276},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C147176958","wikidata":"https://www.wikidata.org/wiki/Q77590","display_name":"Civil engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3165712","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3165712","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/G1899722019","display_name":"\u6df1\u5ea6\u5b66\u4e60\u8bed\u97f3\u8bc6\u522b\u4e2d\u7684\u5feb\u901f\u9ad8\u6548\u81ea\u9002\u5e94\u65b9\u6cd5\u7814\u7a76","funder_award_id":"62071288","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3537961753","display_name":null,"funder_award_id":"62122050","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":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W262275730","https://openalex.org/W1494198834","https://openalex.org/W1901129140","https://openalex.org/W1991139021","https://openalex.org/W2064675550","https://openalex.org/W2117678320","https://openalex.org/W2194775991","https://openalex.org/W2221409856","https://openalex.org/W2302255633","https://openalex.org/W2460742184","https://openalex.org/W2510642588","https://openalex.org/W2550143307","https://openalex.org/W2552071709","https://openalex.org/W2558649592","https://openalex.org/W2726515241","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2803322398","https://openalex.org/W2890244912","https://openalex.org/W2891054259","https://openalex.org/W2891405874","https://openalex.org/W2891833136","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2962935966","https://openalex.org/W2963773971","https://openalex.org/W2972767900","https://openalex.org/W2973062255","https://openalex.org/W3000358149","https://openalex.org/W3004940340","https://openalex.org/W3008003372","https://openalex.org/W3008762051","https://openalex.org/W3013139777","https://openalex.org/W3013934216","https://openalex.org/W3015199127","https://openalex.org/W3015372568","https://openalex.org/W3016232124","https://openalex.org/W3017474798","https://openalex.org/W3020336359","https://openalex.org/W3032514799","https://openalex.org/W3032969657","https://openalex.org/W3049278490","https://openalex.org/W3094380169","https://openalex.org/W3096408984","https://openalex.org/W3096893582","https://openalex.org/W3099330747","https://openalex.org/W3105928222","https://openalex.org/W3124972797","https://openalex.org/W3133834828","https://openalex.org/W3143843080","https://openalex.org/W3151851237","https://openalex.org/W3160241658","https://openalex.org/W3161201807","https://openalex.org/W3161480375","https://openalex.org/W3163652268","https://openalex.org/W3163842642","https://openalex.org/W3171278394","https://openalex.org/W3185109982","https://openalex.org/W3195010976","https://openalex.org/W3197823486","https://openalex.org/W4288091954","https://openalex.org/W6739901393","https://openalex.org/W6751512325","https://openalex.org/W6769178842","https://openalex.org/W6774995033","https://openalex.org/W6779752190","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W1983399396","https://openalex.org/W2027320759","https://openalex.org/W2041788160","https://openalex.org/W2004803009","https://openalex.org/W2003241894","https://openalex.org/W2142219702","https://openalex.org/W2008772465","https://openalex.org/W3198383819","https://openalex.org/W1983271292","https://openalex.org/W2044145313"],"abstract_inverted_index":{"Continuous":[0],"speech":[1,165],"separation":[2],"(CSS)":[3],"aims":[4],"at":[5],"separating":[6],"overlap-free":[7],"targets":[8],"from":[9,102],"a":[10,88],"long,":[11],"partially-overlapped":[12],"recording.":[13],"Though":[14],"it":[15],"has":[16],"shown":[17],"promising":[18],"results,":[19],"the":[20,47,54,60,64,83,107,113,134,149,159,163,177],"origin":[21],"CSS":[22,61],"framework":[23],"does":[24],"not":[25],"consider":[26],"cross-window":[27],"information":[28,69,128,161],"and":[29,44,66,106,143,166],"long-span":[30,48,84,160],"dependency.":[31],"To":[32],"alleviate":[33],"these":[34,180],"limitations,":[35],"this":[36],"work":[37],"introduces":[38],"two":[39,181],"novel":[40],"methods":[41],"to":[42,80,99,130,138],"implicitly":[43],"explicitly":[45],"capture":[46,82,158],"knowledge,":[49],"respectively.":[50],"We":[51],"firstly":[52],"apply":[53],"dual-path":[55],"(DP)":[56],"modeling":[57,141],"architecture":[58],"for":[59,91],"framework,":[62],"where":[63],"within":[65],"across":[67,133],"window":[68],"are":[70,174],"jointly":[71],"modeled":[72],"by":[73],"alternating":[74],"stacked":[75],"local-global":[76],"processing":[77],"modules.":[78],"Secondly,":[79],"further":[81,172],"dependency,":[85],"we":[86],"introduce":[87],"memory-based":[89,122],"model":[90,123],"CSS.":[92],"An":[93],"additional":[94],"memory":[95,114],"pool":[96,116],"is":[97,110],"designed":[98],"extract":[100],"embedding":[101,115],"each":[103],"small":[104],"window,":[105],"inter-window":[108],"commutation":[109],"established":[111],"above":[112],"through":[117],"an":[118],"attention":[119],"mechanism.":[120],"This":[121],"can":[124,156],"precisely":[125],"control":[126],"what":[127],"needs":[129],"be":[131],"transferred":[132],"windows,":[135],"thus":[136],"leading":[137],"both":[139,154],"improved":[140],"capacity":[142],"interpretability.":[144],"The":[145],"experimental":[146],"results":[147],"on":[148],"LibriCSS":[150],"dataset":[151],"show":[152],"that":[153],"strategies":[155],"well":[157],"of":[162,179],"continuous":[164],"significantly":[167],"improve":[168],"system":[169],"performance.":[170],"Moreover,":[171],"improvements":[173],"observed":[175],"with":[176],"integration":[178],"methods.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}