{"id":"https://openalex.org/W3031404175","doi":"https://doi.org/10.1109/access.2020.2997871","title":"Multi-Head Self-Attention-Based Deep Clustering for Single-Channel Speech Separation","display_name":"Multi-Head Self-Attention-Based Deep Clustering for Single-Channel Speech Separation","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3031404175","doi":"https://doi.org/10.1109/access.2020.2997871","mag":"3031404175"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.2997871","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2997871","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09099802.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09099802.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082390177","display_name":"Yanliang Jin","orcid":"https://orcid.org/0000-0001-9836-8249"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanliang Jin","raw_affiliation_strings":["Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication, Shanghai Institute for Advanced Communication and Data Science, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9836-8249","affiliations":[{"raw_affiliation_string":"Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication, Shanghai Institute for Advanced Communication and Data Science, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102892588","display_name":"Chunjun Tang","orcid":"https://orcid.org/0000-0003-1242-0777"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenjun Tang","raw_affiliation_strings":["Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication, Shanghai Institute for Advanced Communication and Data Science, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1242-0777","affiliations":[{"raw_affiliation_string":"Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication, Shanghai Institute for Advanced Communication and Data Science, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090025454","display_name":"Qianhong Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianhong Liu","raw_affiliation_strings":["Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication, Shanghai Institute for Advanced Communication and Data Science, Shanghai University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication, Shanghai Institute for Advanced Communication and Data Science, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100322682","display_name":"Yan Wang","orcid":"https://orcid.org/0000-0002-3984-6973"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Wang","raw_affiliation_strings":["Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication, Shanghai Institute for Advanced Communication and Data Science, Shanghai University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication, Shanghai Institute for Advanced Communication and Data Science, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.2811,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.88833812,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"8","issue":null,"first_page":"100013","last_page":"100021"},"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":0.9993000030517578,"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":0.7618862390518188},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6044461131095886},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5534904599189758},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.49241316318511963},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.48095789551734924},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43195950984954834},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.41559818387031555},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3501344621181488},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1874811053276062},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14989230036735535},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.07421654462814331}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7618862390518188},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6044461131095886},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5534904599189758},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.49241316318511963},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.48095789551734924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43195950984954834},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.41559818387031555},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3501344621181488},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1874811053276062},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14989230036735535},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.07421654462814331},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2020.2997871","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2997871","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09099802.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:068eef1f3e76459d8048995dd22f351c","is_oa":true,"landing_page_url":"https://doaj.org/article/068eef1f3e76459d8048995dd22f351c","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":"IEEE Access, Vol 8, Pp 100013-100021 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.2997871","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2997871","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09099802.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6700000166893005}],"awards":[{"id":"https://openalex.org/G1049196916","display_name":null,"funder_award_id":"10734","funder_id":"https://openalex.org/F4320335087","funder_display_name":"Innovate UK"},{"id":"https://openalex.org/G3644517305","display_name":null,"funder_award_id":"61771299","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4302736577","display_name":null,"funder_award_id":"778305","funder_id":"https://openalex.org/F4320338348","funder_display_name":"H2020 Environment"},{"id":"https://openalex.org/G6472134177","display_name":null,"funder_award_id":"778305","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G7633694456","display_name":null,"funder_award_id":"2018YFB2101303","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8925783075","display_name":null,"funder_award_id":"12511503303","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"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320335087","display_name":"Innovate UK","ror":"https://ror.org/05ar5fy68"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320337104","display_name":"Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences","ror":"https://ror.org/04nytyj38"},{"id":"https://openalex.org/F4320338348","display_name":"H2020 Environment","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3031404175.pdf","grobid_xml":"https://content.openalex.org/works/W3031404175.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W185399533","https://openalex.org/W1552314771","https://openalex.org/W1790748249","https://openalex.org/W1991139021","https://openalex.org/W2003850925","https://openalex.org/W2031647436","https://openalex.org/W2044222806","https://openalex.org/W2060822897","https://openalex.org/W2064675550","https://openalex.org/W2069681747","https://openalex.org/W2082183045","https://openalex.org/W2087368178","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2377713473","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2561557072","https://openalex.org/W2610674366","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2767989436","https://openalex.org/W2789511664","https://openalex.org/W2794289187","https://openalex.org/W2890111732","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2963021258","https://openalex.org/W2963560594","https://openalex.org/W2963590118","https://openalex.org/W2972369255","https://openalex.org/W2972542211","https://openalex.org/W3099330747","https://openalex.org/W3123318516","https://openalex.org/W3124794156","https://openalex.org/W3124972797","https://openalex.org/W4289665794","https://openalex.org/W4385245566","https://openalex.org/W6607486085","https://openalex.org/W6709535953","https://openalex.org/W6739901393","https://openalex.org/W6746213830","https://openalex.org/W6746565888"],"related_works":["https://openalex.org/W2071676784","https://openalex.org/W4292513318","https://openalex.org/W4308092240","https://openalex.org/W2287611352","https://openalex.org/W4298130764","https://openalex.org/W320684304","https://openalex.org/W1509352139","https://openalex.org/W3097502728","https://openalex.org/W2804364458","https://openalex.org/W2791440692"],"abstract_inverted_index":{"Turning":[0],"attention":[1],"to":[2,26,42,96],"a":[3,21,127],"particular":[4],"speaker":[5],"when":[6],"many":[7,132],"people":[8],"talk":[9],"simultaneously":[10],"is":[11,19],"known":[12],"as":[13],"the":[14,36,52,65,78,91,107,122],"cocktail":[15],"party":[16],"problem.":[17,61],"It":[18],"still":[20],"tough":[22],"task":[23],"that":[24,39],"remained":[25],"be":[27],"solved":[28],"especially":[29],"for":[30,59],"single-channel":[31],"speech":[32],"separation.":[33],"Inspired":[34],"by":[35],"physiological":[37],"phenomenon":[38],"humans":[40],"tend":[41],"distinguish":[43],"some":[44],"attractive":[45],"sounds":[46],"from":[47],"mixed":[48],"signals,":[49],"we":[50],"propose":[51],"multi-head":[53,72,83],"self-attention":[54,73,84],"deep":[55,68],"clustering":[56,69],"network":[57,70],"(ADCNet)":[58],"this":[60],"We":[62,88,100],"creatively":[63],"combine":[64],"widely":[66],"used":[67],"with":[71,131],"mechanism":[74],"and":[75,102,115],"exploit":[76],"how":[77],"number":[79],"of":[80],"heads":[81],"in":[82],"affects":[85],"separation":[86],"performance.":[87,99],"also":[89],"adopt":[90],"density-based":[92],"canopy":[93],"K-means":[94],"algorithm":[95],"further":[97],"improve":[98],"trained":[101],"evaluated":[103],"our":[104],"system":[105],"using":[106],"Wall":[108],"Street":[109],"Journal":[110],"dataset":[111],"(WSJ0)":[112],"on":[113],"two":[114],"three":[116],"talker":[117],"mixtures.":[118],"Experimental":[119],"results":[120],"show":[121],"new":[123],"approach":[124],"can":[125],"achieve":[126],"better":[128],"performance":[129],"compared":[130],"advanced":[133],"models.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}