{"id":"https://openalex.org/W3133848124","doi":"https://doi.org/10.23919/eusipco54536.2021.9616142","title":"Continuous Speech Separation with Ad Hoc Microphone Arrays","display_name":"Continuous Speech Separation with Ad Hoc Microphone Arrays","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3133848124","doi":"https://doi.org/10.23919/eusipco54536.2021.9616142","mag":"3133848124"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616142","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616142","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"2021 29th European Signal Processing Conference (EUSIPCO)","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/A5100408281","display_name":"Dongmei Wang","orcid":"https://orcid.org/0000-0002-6930-0066"},"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":true,"raw_author_name":"Dongmei Wang","raw_affiliation_strings":["Microsoft,Redmond,WA,USA"],"affiliations":[{"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"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"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/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"],"affiliations":[{"raw_affiliation_string":"Microsoft,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,Redmond,WA,USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"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/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":"Tianyan Zhou","raw_affiliation_strings":["Microsoft,Redmond,WA,USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","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"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100408281"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":3.7848,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.97313633,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9995999932289124,"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":0.9986000061035156,"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":0.78804612159729},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6645071506500244},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5970683693885803},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.46586158871650696},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.44841116666793823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.78804612159729},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6645071506500244},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5970683693885803},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.46586158871650696},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.44841116666793823},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616142","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616142","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"2021 29th European Signal Processing Conference (EUSIPCO)","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":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W262275730","https://openalex.org/W1494198834","https://openalex.org/W2460742184","https://openalex.org/W2517616541","https://openalex.org/W2591810467","https://openalex.org/W2594789261","https://openalex.org/W2631415506","https://openalex.org/W2757672955","https://openalex.org/W2803322398","https://openalex.org/W2803583024","https://openalex.org/W2889503488","https://openalex.org/W2889664202","https://openalex.org/W2898268964","https://openalex.org/W2963403868","https://openalex.org/W2964391865","https://openalex.org/W2972693890","https://openalex.org/W2996322586","https://openalex.org/W3008283340","https://openalex.org/W3008762051","https://openalex.org/W3015372568","https://openalex.org/W3016232124","https://openalex.org/W3094893851","https://openalex.org/W3095809392","https://openalex.org/W3097700828","https://openalex.org/W3100338867","https://openalex.org/W3104196160","https://openalex.org/W3106603336","https://openalex.org/W3113290170","https://openalex.org/W3131090526","https://openalex.org/W3140651083","https://openalex.org/W3163842642","https://openalex.org/W3171278394","https://openalex.org/W3173811143","https://openalex.org/W4298857741","https://openalex.org/W4385245566","https://openalex.org/W6735011343","https://openalex.org/W6739901393","https://openalex.org/W6744711567","https://openalex.org/W6782142667","https://openalex.org/W6784747387","https://openalex.org/W6785534053","https://openalex.org/W6786372767","https://openalex.org/W6787607767","https://openalex.org/W6790506427"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2769861442","https://openalex.org/W2120442551","https://openalex.org/W1980506188","https://openalex.org/W2112728813","https://openalex.org/W4240587264","https://openalex.org/W2011788874","https://openalex.org/W2900122540","https://openalex.org/W2149163000","https://openalex.org/W2963983801"],"abstract_inverted_index":{"Speech":[0],"separation":[1,80,184],"has":[2],"been":[3],"shown":[4],"effective":[5],"for":[6,81,91,132,163,192,199],"multi-talker":[7],"speech":[8,71,79,109,194],"recognition.":[9],"Under":[10],"the":[11,18,32,53,57,95,121,134,151,157,182,189],"ad":[12,58,96,122],"hoc":[13,59,97,123],"microphone":[14],"array":[15,19,98,124],"setup":[16],"where":[17],"consists":[20],"of":[21,36,56,94,169,172],"spatially":[22],"distributed":[23],"asynchronous":[24],"microphones,":[25],"additional":[26],"challenges":[27],"must":[28],"be":[29],"overcome":[30],"as":[31],"geometry":[33],"and":[34,141,155],"number":[35],"microphones":[37],"are":[38,75,104],"unknown":[39],"beforehand.":[40],"Prior":[41],"studies":[42],"show,":[43],"with":[44,195],"a":[45,88,108,165],"spatial-temporal-interleaving":[46],"structure,":[47],"neural":[48],"networks":[49],"can":[50,186],"efficiently":[51],"utilize":[52],"multi-channel":[54],"signals":[55],"array.":[60],"In":[61,100],"this":[62,67],"paper,":[63],"we":[64,86],"further":[65],"extend":[66],"approach":[68],"to":[69,77,106,149],"continuous":[70,83,170],"separation.":[72],"Several":[73],"techniques":[74],"introduced":[76],"enable":[78],"real":[82,142],"recordings.":[84,143],"First,":[85],"apply":[87],"transformer-based":[89],"network":[90],"spatio-temporal":[92],"modeling":[93],"signals.":[99],"addition,":[101],"two":[102],"methods":[103],"proposed":[105,183],"mitigate":[107],"duplication":[110],"problem":[111],"during":[112],"single":[113,152,200],"talker":[114,201],"segments,":[115],"which":[116],"seems":[117],"more":[118],"severe":[119],"in":[120],"scenarios.":[125],"One":[126],"method":[127,185],"is":[128,146],"device":[129],"distortion":[130],"simulation":[131],"reducing":[133],"acoustic":[135],"mismatch":[136],"between":[137],"simulated":[138],"training":[139],"data":[140],"The":[144],"other":[145],"speaker":[147,153],"counting":[148],"detect":[150],"segments":[154],"merge":[156],"output":[158],"signal":[159],"channels.":[160],"Experimental":[161],"results":[162],"AdHoc-LibiCSS,":[164],"new":[166],"dataset":[167],"consisting":[168],"recordings":[171],"concatenated":[173],"LibriSpeech":[174],"utterances":[175],"obtained":[176],"by":[177],"multiple":[178],"different":[179],"devices,":[180],"show":[181],"significantly":[187],"improve":[188],"ASR":[190],"accuracy":[191],"overlapped":[193],"little":[196],"performance":[197],"degradation":[198],"segments.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}