{"id":"https://openalex.org/W4221164375","doi":"https://doi.org/10.1109/icassp43922.2022.9746649","title":"The CUHK-Tencent Speaker Diarization System for the ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challenge","display_name":"The CUHK-Tencent Speaker Diarization System for the ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challenge","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221164375","doi":"https://doi.org/10.1109/icassp43922.2022.9746649"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746649","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/A5100368048","display_name":"Na Li","orcid":"https://orcid.org/0000-0001-9545-3050"},"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/A5025119324","display_name":"Xixin Wu","orcid":"https://orcid.org/0000-0001-9543-1572"},"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":"Xixin Wu","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/A5089153961","display_name":"Lingwei Meng","orcid":"https://orcid.org/0000-0003-1028-6017"},"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":"Lingwei 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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062761975","display_name":"Jiawen Kang","orcid":"https://orcid.org/0000-0002-8218-3490"},"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":"Jiawen Kang","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/A5101474128","display_name":"Haibin Wu","orcid":"https://orcid.org/0000-0001-7166-5534"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Haibin Wu","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"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/A5062034286","display_name":"Dan Su","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":"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":"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":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9161","last_page":"9165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9994999766349792,"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":0.9539552927017212},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.785560131072998},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7284871339797974},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6488640308380127},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.591793954372406},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5878839492797852},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4706116318702698},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.19005882740020752},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.06218460202217102}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9539552927017212},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.785560131072998},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7284871339797974},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6488640308380127},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.591793954372406},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5878839492797852},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4706116318702698},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.19005882740020752},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.06218460202217102},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"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/icassp43922.2022.9746649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746649","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":[],"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/W2148613904","https://openalex.org/W2169264834","https://openalex.org/W2560648290","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2909607850","https://openalex.org/W2928165649","https://openalex.org/W2952218014","https://openalex.org/W2972949456","https://openalex.org/W2989790778","https://openalex.org/W3015598461","https://openalex.org/W3025260599","https://openalex.org/W3096494136","https://openalex.org/W3097878195","https://openalex.org/W3099330747","https://openalex.org/W3140898556","https://openalex.org/W3157070662","https://openalex.org/W3162899647","https://openalex.org/W3196117288","https://openalex.org/W3198482860","https://openalex.org/W3207834622","https://openalex.org/W4224916247","https://openalex.org/W4224925136","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6761176859"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"our":[3],"speaker":[4,41],"diarization":[5,26,143],"system":[6,85,107],"submitted":[7],"to":[8,86,104],"the":[9,37,40,44,57,88,91,106,110,142],"Multi-channel":[10],"Multi-party":[11],"Meeting":[12],"Transcription":[13],"(M2MeT)":[14],"challenge,":[15],"where":[16],"Mandarin":[17],"meeting":[18,35],"data":[19,99],"were":[20],"recorded":[21],"in":[22,127,141],"multi-channel":[23],"format":[24],"for":[25,53,122],"and":[27,43,69,138],"automatic":[28],"speech":[29,49],"recognition":[30],"(ASR)":[31],"tasks.":[32],"In":[33],"these":[34],"scenarios,":[36],"uncertainty":[38],"of":[39,47,90,135],"number":[42],"high":[45],"ratio":[46],"overlapped":[48],"present":[50],"great":[51],"challenges":[52],"diarization.":[54],"Based":[55],"on":[56],"assumption":[58],"that":[59],"there":[60],"is":[61,116,132],"valuable":[62],"complementary":[63],"information":[64],"between":[65,113],"acoustic":[66],"features,":[67,71],"spatial-related":[68],"speaker-related":[70],"we":[72,96,125],"propose":[73,97],"a":[74,98,133],"multi-level":[75],"feature":[76],"fusion":[77,134],"mechanism":[78],"based":[79],"target-speaker":[80],"voice":[81],"activity":[82],"detection":[83],"(FFM-TS-VAD)":[84],"improve":[87,105],"performance":[89],"conventional":[92],"TS-VAD":[93],"system.":[94],"Furthermore,":[95],"augmentation":[100],"method":[101],"during":[102],"training":[103],"robustness":[108],"when":[109],"angular":[111],"difference":[112],"two":[114],"speakers":[115],"relatively":[117],"small.":[118],"We":[119],"provide":[120],"comparisons":[121],"different":[123],"sub-systems":[124,137],"used":[126],"M2MeT":[128],"challenge.":[129],"Our":[130],"submission":[131],"several":[136],"ranks":[139],"second":[140],"task.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}