{"id":"https://openalex.org/W4224916247","doi":"https://doi.org/10.1109/icassp43922.2022.9747343","title":"Multi-Channel Speaker Diarization Using Spatial Features for Meetings","display_name":"Multi-Channel Speaker Diarization Using Spatial Features for Meetings","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224916247","doi":"https://doi.org/10.1109/icassp43922.2022.9747343"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747343","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/A5077304193","display_name":"Naijun Zheng","orcid":"https://orcid.org/0000-0001-8321-5418"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Naijun Zheng","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368213","display_name":"Na Li","orcid":"https://orcid.org/0000-0002-4627-036X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Na Li","raw_affiliation_strings":["Tencent AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004643540","display_name":"Jianwei Yu","orcid":"https://orcid.org/0000-0002-2449-1436"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"JianWei Yu","raw_affiliation_strings":["Tencent AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106404246","display_name":"Chao Weng","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Weng","raw_affiliation_strings":["Tencent AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075183307","display_name":"Dan Su","orcid":"https://orcid.org/0000-0001-5746-9545"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Su","raw_affiliation_strings":["Tencent AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011251750","display_name":"XunYing Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"XunYing Liu","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4765,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.83633613,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7337","last_page":"7341"},"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":0.9998999834060669,"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":0.9988999962806702,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.9361696839332581},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7880055904388428},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.7168630361557007},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7043347358703613},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4233446419239044},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3336978554725647},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.17020809650421143}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9361696839332581},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7880055904388428},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.7168630361557007},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7043347358703613},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4233446419239044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3336978554725647},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.17020809650421143}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747343","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/4","display_name":"Quality Education","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2081074144","https://openalex.org/W2113638573","https://openalex.org/W2125336414","https://openalex.org/W2141398670","https://openalex.org/W2148613904","https://openalex.org/W2169264834","https://openalex.org/W2194775991","https://openalex.org/W2216290105","https://openalex.org/W2763188033","https://openalex.org/W2808631503","https://openalex.org/W2909607850","https://openalex.org/W2952218014","https://openalex.org/W2989790778","https://openalex.org/W3015598461","https://openalex.org/W3015780472","https://openalex.org/W3016218307","https://openalex.org/W3025260599","https://openalex.org/W3099330747","https://openalex.org/W3128293163","https://openalex.org/W3157070662","https://openalex.org/W3160741541","https://openalex.org/W3161587262","https://openalex.org/W3161927588","https://openalex.org/W3162899647","https://openalex.org/W3198482860","https://openalex.org/W6678809451","https://openalex.org/W6784464189"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1521049138","https://openalex.org/W2144208207","https://openalex.org/W1813780412","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2148232863","https://openalex.org/W2160753975","https://openalex.org/W2118860825","https://openalex.org/W2161543916"],"abstract_inverted_index":{"Speaker":[0],"identification":[1],"for":[2,9],"overlapped":[3,52,108],"speech":[4,53],"presents":[5],"a":[6,65,142],"great":[7],"challenge":[8],"speaker":[10,34],"diarization":[11,35,44,91,132],"tasks":[12],"in":[13,50,103,129],"meeting":[14],"scenarios.":[15],"In":[16,37],"order":[17],"to":[18,68,96,106],"overcome":[19],"such":[20],"challenges,":[21],"several":[22],"overlap-aware":[23,138],"resegmentation":[24],"methods":[25],"based":[26,88],"on":[27,89,112],"deep":[28],"learning":[29,58],"have":[30,47],"been":[31],"integrated":[32],"into":[33],"systems.":[36],"this":[38],"paper":[39],"we":[40],"propose":[41],"two":[42],"multi-channel":[43],"systems":[45,94,123],"which":[46],"enhanced":[48],"capability":[49],"detecting":[51],"and":[54,78,127],"identify":[55],"speakers":[56,87,102],"via":[57],"spatial":[59],"features.":[60],"The":[61],"first":[62],"system":[63,81,140],"applies":[64],"multi-look":[66],"strategy":[67],"train":[69],"networks":[70],"without":[71],"given":[72],"the":[73,79,83,98,113,118],"speakers\u2019":[74],"direction":[75],"of":[76,85,101,121,131],"arrival(DOA),":[77],"other":[80],"estimates":[82],"DOA":[84],"target":[86],"existing":[90],"results.":[92],"Both":[93],"aim":[95],"estimate":[97],"voice":[99],"activity":[100],"different":[104],"directions":[105],"handle":[107],"speech.":[109],"Experimental":[110],"results":[111],"AMI":[114],"corpus":[115],"show":[116],"that":[117],"relative":[119],"improvements":[120],"both":[122],"can":[124],"reach":[125],"9.4%":[126],"18.1%":[128],"term":[130],"error":[133],"rate":[134],"(DER)":[135],"against":[136],"an":[137],"single-channel":[139],"with":[141],"BeamformIt":[143],"front-end.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}