{"id":"https://openalex.org/W3207360934","doi":"https://doi.org/10.1109/icassp43922.2022.9746876","title":"VarArray: Array-Geometry-Agnostic Continuous Speech Separation","display_name":"VarArray: Array-Geometry-Agnostic Continuous Speech Separation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3207360934","doi":"https://doi.org/10.1109/icassp43922.2022.9746876","mag":"3207360934"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746876","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":"conference-paper","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/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, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100363470","display_name":"Xiaofei Wang","orcid":"https://orcid.org/0000-0002-7223-1030"},"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":"Xiaofei Wang","raw_affiliation_strings":["Microsoft, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100408286","display_name":"Dongmei Wang","orcid":"https://orcid.org/0000-0002-9588-7112"},"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":"Dongmei Wang","raw_affiliation_strings":["Microsoft, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106627865","display_name":"Min Tang","orcid":"https://orcid.org/0009-0006-3428-9967"},"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":"Min Tang","raw_affiliation_strings":["Microsoft, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046470928","display_name":"Zirun Zhu","orcid":null},"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":"Zirun Zhu","raw_affiliation_strings":["Microsoft, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"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, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016279564","display_name":"Naoyuki Kanda","orcid":"https://orcid.org/0000-0002-8628-3288"},"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":"Naoyuki Kanda","raw_affiliation_strings":["Microsoft, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6027","last_page":"6031"},"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":0.9991999864578247,"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":0.9986000061035156,"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":0.7497344017028809},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5416401624679565},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5125579833984375},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4715326428413391},{"id":"https://openalex.org/keywords/information-geometry","display_name":"Information geometry","score":0.44109901785850525},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.43273890018463135},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.4265690743923187},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.4210379719734192},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.3478245735168457},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33484727144241333},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17165890336036682},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.12451177835464478},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09131267666816711}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7497344017028809},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5416401624679565},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5125579833984375},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4715326428413391},{"id":"https://openalex.org/C109546454","wikidata":"https://www.wikidata.org/wiki/Q3798604","display_name":"Information geometry","level":4,"score":0.44109901785850525},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.43273890018463135},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.4265690743923187},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.4210379719734192},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.3478245735168457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33484727144241333},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17165890336036682},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.12451177835464478},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09131267666816711},{"id":"https://openalex.org/C12520029","wikidata":"https://www.wikidata.org/wiki/Q1147161","display_name":"Scalar curvature","level":3,"score":0.0},{"id":"https://openalex.org/C195065555","wikidata":"https://www.wikidata.org/wiki/Q214881","display_name":"Curvature","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746876","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":[{"id":"https://metadata.un.org/sdg/16","score":0.5600000023841858,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W262275730","https://openalex.org/W1983812858","https://openalex.org/W2030486566","https://openalex.org/W2117678320","https://openalex.org/W2125336414","https://openalex.org/W2148613904","https://openalex.org/W2219249508","https://openalex.org/W2734774145","https://openalex.org/W2803322398","https://openalex.org/W2889503488","https://openalex.org/W2890244912","https://openalex.org/W2900893004","https://openalex.org/W2939246703","https://openalex.org/W3008283340","https://openalex.org/W3008762051","https://openalex.org/W3015199127","https://openalex.org/W3015372568","https://openalex.org/W3015834770","https://openalex.org/W3016232124","https://openalex.org/W3025165719","https://openalex.org/W3091848479","https://openalex.org/W3093579165","https://openalex.org/W3094893851","https://openalex.org/W3097777922","https://openalex.org/W3106426924","https://openalex.org/W3140783160","https://openalex.org/W3162315798","https://openalex.org/W3163842642","https://openalex.org/W3171278394","https://openalex.org/W3187990717","https://openalex.org/W3196660995","https://openalex.org/W3197674197","https://openalex.org/W3198100319","https://openalex.org/W3198654230","https://openalex.org/W3207728800","https://openalex.org/W6688816777","https://openalex.org/W6784614252"],"related_works":["https://openalex.org/W2161947961","https://openalex.org/W2116623987","https://openalex.org/W1488173215","https://openalex.org/W2165869870","https://openalex.org/W1491017269","https://openalex.org/W1977167953","https://openalex.org/W2155276444","https://openalex.org/W1993694758","https://openalex.org/W1607399658","https://openalex.org/W2149163000"],"abstract_inverted_index":{"Continuous":[0],"speech":[1,16,29,69,119],"separation":[2,30,120],"using":[3,95,166],"a":[4,96,131],"microphone":[5],"array":[6],"was":[7,86],"shown":[8],"to":[9,39,112,134],"be":[10],"promising":[11],"in":[12,19,78,124,162],"dealing":[13],"with":[14,88],"the":[15,48,52,114,117,140,155,163],"overlap":[17],"problem":[18],"natural":[20],"conversation":[21],"transcription.":[22],"This":[23],"paper":[24],"proposes":[25],"VarArray,":[26],"an":[27,79],"array-geometry-agnostic":[28,135],"neural":[31],"network":[32],"model.":[33],"The":[34,55,127],"proposed":[35,56,63,128],"model":[36,129],"is":[37],"applicable":[38],"any":[40],"number":[41],"of":[42,139,150],"microphones":[43],"without":[44],"retraining":[45],"while":[46],"leveraging":[47],"nonlinear":[49],"correlation":[50],"between":[51],"input":[53],"channels.":[54],"method":[57],"adapts":[58],"different":[59],"elements":[60],"that":[61,116],"were":[62],"before":[64],"separately,":[65],"including":[66],"transform-average-concatenate,":[67],"conformer":[68],"separation,":[70],"and":[71,75,81,152,158],"inter-channel":[72],"phase":[73],"differences,":[74],"combines":[76],"them":[77],"efficient":[80],"cohesive":[82],"way.":[83],"Large-scale":[84],"evaluation":[85,159],"performed":[87],"two":[89],"real":[90],"meeting":[91],"transcription":[92,99],"tasks":[93],"by":[94],"fully":[97],"developed":[98],"system":[100,121],"requiring":[101],"no":[102,167],"prior":[103],"knowledge":[104],"such":[105],"as":[106],"reference":[107],"segmentations,":[108],"which":[109],"allowed":[110],"us":[111],"measure":[113],"impact":[115],"continuous":[118],"could":[122],"have":[123],"realistic":[125],"settings.":[126],"outperformed":[130],"previous":[132],"approach":[133],"modeling":[136],"for":[137,154],"all":[138],"geometry":[141],"configurations":[142],"considered,":[143],"achieving":[144],"asclite-based":[145],"speaker-agnostic":[146],"word":[147],"error":[148],"rates":[149],"17.5%":[151],"20.4%":[153],"AMI":[156],"development":[157],"sets,":[160],"respectively,":[161],"end-to-end":[164],"setting":[165],"ground-truth":[168],"segmentations.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}