{"id":"https://openalex.org/W3160241658","doi":"https://doi.org/10.1109/icassp39728.2021.9414176","title":"Rethinking The Separation Layers In Speech Separation Networks","display_name":"Rethinking The Separation Layers In Speech Separation Networks","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160241658","doi":"https://doi.org/10.1109/icassp39728.2021.9414176","mag":"3160241658"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5048439332","display_name":"Yi Luo","orcid":"https://orcid.org/0000-0002-7447-3885"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yi Luo","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108961732","display_name":"Zhuo Chen","orcid":"https://orcid.org/0009-0007-3882-3810"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070114472","display_name":"Cong Han","orcid":"https://orcid.org/0000-0003-2121-000X"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cong Han","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","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":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103218426","display_name":"Tianyan Zhou","orcid":"https://orcid.org/0000-0003-3238-2982"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tianyan Zhou","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033351155","display_name":"Nima Mesgarani","orcid":"https://orcid.org/0000-0002-2987-759X"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nima Mesgarani","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5048439332"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":1.0665,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.76200135,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9972000122070312,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9872000217437744,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.7816115617752075},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.643602728843689},{"id":"https://openalex.org/keywords/separation-of-concerns","display_name":"Separation of concerns","score":0.513538122177124},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.42731037735939026},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.4184590280056},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20425879955291748},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.19843629002571106},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.11087259650230408},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11020070314407349},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1048586368560791}],"concepts":[{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.7816115617752075},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.643602728843689},{"id":"https://openalex.org/C76214141","wikidata":"https://www.wikidata.org/wiki/Q2465506","display_name":"Separation of concerns","level":3,"score":0.513538122177124},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.42731037735939026},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.4184590280056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20425879955291748},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.19843629002571106},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.11087259650230408},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11020070314407349},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1048586368560791},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2117678320","https://openalex.org/W2158216966","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2734774145","https://openalex.org/W2891405874","https://openalex.org/W2898268964","https://openalex.org/W2909607850","https://openalex.org/W2939246703","https://openalex.org/W2944972166","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W2963452667","https://openalex.org/W2964121744","https://openalex.org/W2968723745","https://openalex.org/W2972492143","https://openalex.org/W2972541922","https://openalex.org/W2972767900","https://openalex.org/W2973062255","https://openalex.org/W2982456909","https://openalex.org/W3008003372","https://openalex.org/W3008762051","https://openalex.org/W3008880747","https://openalex.org/W3015199127","https://openalex.org/W3015372568","https://openalex.org/W3016232124","https://openalex.org/W3027008958","https://openalex.org/W3035268204","https://openalex.org/W3094821064","https://openalex.org/W3099330747","https://openalex.org/W3104196160","https://openalex.org/W3105928222","https://openalex.org/W3148310299","https://openalex.org/W3185109982","https://openalex.org/W6631190155","https://openalex.org/W6751512325","https://openalex.org/W6755462816","https://openalex.org/W6762182681","https://openalex.org/W6768815455","https://openalex.org/W6769802879","https://openalex.org/W6774687970","https://openalex.org/W6774995033","https://openalex.org/W6777776875"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2383482627","https://openalex.org/W2392054573","https://openalex.org/W2327090586","https://openalex.org/W1586505680","https://openalex.org/W2031042346","https://openalex.org/W4391311396","https://openalex.org/W4384788395","https://openalex.org/W2500355910"],"abstract_inverted_index":{"Modules":[0],"in":[1,98],"all":[2],"existing":[3],"speech":[4],"separation":[5,41,55,66,127,151,173],"networks":[6],"can":[7,63,71],"be":[8,72],"categorized":[9],"into":[10],"single-input-multi-output":[11],"(SIMO)":[12],"modules":[13,19,27,81,140],"and":[14,25,33,101,141,166],"single-input-single-output":[15],"(SISO)":[16],"modules.":[17,103],"SIMO":[18,45,80,100,139],"generate":[20],"more":[21],"outputs":[22],"than":[23],"input,":[24],"SISO":[26,61,77,102],"keep":[28],"the":[29,35,38,65,76,99,109,126,136,154,162,172],"numbers":[30],"of":[31,40,138],"input":[32],"output":[34],"same.":[36],"While":[37],"majority":[39],"models":[42,94,145],"only":[43],"contain":[44],"architectures,":[46],"it":[47],"has":[48],"also":[49],"been":[50],"shown":[51],"that":[52,106,143],"certain":[53],"two-stage":[54],"systems":[56],"integrated":[57],"with":[58,95,108,117],"a":[59,113,118],"post-enhancement":[60],"module":[62],"improve":[64,125],"quality.":[67],"Why":[68],"performance":[69,128],"improvements":[70],"achieved":[73],"by":[74,92],"incorporating":[75],"modules?":[78],"Are":[79],"always":[82],"necessary?":[83],"In":[84],"this":[85],"paper,":[86],"we":[87],"empirically":[88],"examine":[89],"those":[90],"questions":[91],"designing":[93],"varying":[96],"configurations":[97],"We":[104,133],"show":[105,142],"comparing":[107],"standard":[110],"SIMO-only":[111],"design,":[112],"mixed":[114],"SIMO-SISO":[115],"design":[116,164],"same":[119],"model":[120,163],"size":[121],"is":[122,174],"able":[123,148],"to":[124,149,160],"especially":[129],"under":[130],"low-overlap":[131],"conditions.":[132],"further":[134],"validate":[135],"necessity":[137],"SISO-only":[144],"are":[146],"still":[147],"perform":[150],"without":[152],"sacrificing":[153],"performance.":[155],"The":[156],"observations":[157],"allow":[158],"us":[159],"rethink":[161],"paradigm":[165],"present":[167],"different":[168],"views":[169],"on":[170],"how":[171],"performed.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}