{"id":"https://openalex.org/W3210134537","doi":"https://doi.org/10.1109/icassp43922.2022.9746394","title":"Continuous Speech Separation with Recurrent Selective Attention Network","display_name":"Continuous Speech Separation with Recurrent Selective Attention Network","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3210134537","doi":"https://doi.org/10.1109/icassp43922.2022.9746394","mag":"3210134537"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746394","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746394","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5034640924","display_name":"Yixuan Zhang","orcid":"https://orcid.org/0000-0002-1343-2713"},"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"]},{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yixuan Zhang","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA","The Ohio State University, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106557560","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0002-8483-1578"},"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","Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101674460","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0002-3101-7011"},"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":"Jian Wu","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"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":"Takuya Yoshioka","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062250845","display_name":"Peidong Wang","orcid":"https://orcid.org/0000-0002-7042-0209"},"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":"Peidong Wang","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101749753","display_name":"Zhong Meng","orcid":"https://orcid.org/0000-0001-7814-5929"},"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":"Zhong Meng","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"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":"Jinyu Li","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5034640924"],"corresponding_institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.7355,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.68025276,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6017","last_page":"6021"},"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":0.9998000264167786,"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":0.9993000030517578,"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":0.7829769849777222},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.7326342463493347},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.6211065053939819},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5593984127044678},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5167709589004517},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5009970664978027},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.47268491983413696},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42443692684173584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.384291410446167},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1941930055618286},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08778247237205505}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7829769849777222},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.7326342463493347},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.6211065053939819},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5593984127044678},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5167709589004517},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5009970664978027},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.47268491983413696},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42443692684173584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.384291410446167},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1941930055618286},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08778247237205505},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746394","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746394","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2030486566","https://openalex.org/W2117678320","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2734774145","https://openalex.org/W2803322398","https://openalex.org/W2889503488","https://openalex.org/W2889698889","https://openalex.org/W2891054259","https://openalex.org/W2891644395","https://openalex.org/W2908510526","https://openalex.org/W2950541952","https://openalex.org/W2952218014","https://openalex.org/W2972436155","https://openalex.org/W2972460025","https://openalex.org/W2972956184","https://openalex.org/W2980451698","https://openalex.org/W3000358149","https://openalex.org/W3008283340","https://openalex.org/W3015199127","https://openalex.org/W3016232124","https://openalex.org/W3016400019","https://openalex.org/W3020336359","https://openalex.org/W3032514799","https://openalex.org/W3099330747","https://openalex.org/W3116025434","https://openalex.org/W3163652268","https://openalex.org/W3163842642","https://openalex.org/W3171278394","https://openalex.org/W3185109982","https://openalex.org/W6757817989","https://openalex.org/W6771611251"],"related_works":["https://openalex.org/W1968552888","https://openalex.org/W1527532029","https://openalex.org/W2374116601","https://openalex.org/W3093134843","https://openalex.org/W2378167147","https://openalex.org/W3210777354","https://openalex.org/W2772323916","https://openalex.org/W2281307425","https://openalex.org/W1511346092","https://openalex.org/W2464405057"],"abstract_inverted_index":{"While":[0],"permutation":[1],"invariant":[2],"training":[3],"(PIT)":[4],"based":[5,61],"continuous":[6],"speech":[7,20,123],"separation":[8,25,95],"(CSS)":[9],"significantly":[10],"improves":[11,121],"the":[12,85,90,94,98,103,110,115,122,136],"conversation":[13],"transcription":[14],"accuracy,":[15],"it":[16,31],"often":[17],"suffers":[18],"from":[19,97],"leakages":[21],"and":[22],"failures":[23],"in":[24,84],"at":[26],"\"hot":[27],"spot\"":[28],"regions":[29],"because":[30],"has":[32],"a":[33,55,70],"fixed":[34],"number":[35,57],"of":[36,58,75,138],"output":[37,59],"channels.":[38],"In":[39,66],"this":[40],"paper,":[41],"we":[42,68],"propose":[43,69],"to":[44,51,92,101],"apply":[45],"recurrent":[46],"selective":[47],"attention":[48],"network":[49,91,119],"(RSAN)":[50],"CSS,":[52],"which":[53],"generates":[54],"variable":[56],"channels":[60],"on":[62,109],"active":[63],"speaker":[64],"counting.":[65],"addition,":[67],"novel":[71],"block-wise":[72,131],"dependency":[73,132],"extension":[74],"RSAN":[76],"by":[77],"introducing":[78],"dependencies":[79],"between":[80],"adjacent":[81],"processing":[82],"blocks":[83,100],"CSS":[86,117],"framework.":[87],"It":[88],"enables":[89],"utilize":[93],"results":[96,108],"previous":[99],"facilitate":[102],"current":[104],"block":[105],"processing.":[106],"Experimental":[107],"LibriCSS":[111],"dataset":[112],"show":[113],"that":[114],"RSAN-based":[116],"(RSAN-CSS)":[118],"consistently":[120],"recognition":[124],"accuracy":[125],"over":[126],"PIT-based":[127],"models.":[128],"The":[129],"proposed":[130],"modeling":[133],"further":[134],"boosts":[135],"performance":[137],"RSAN-CSS.":[139]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}