{"id":"https://openalex.org/W4372338350","doi":"https://doi.org/10.1109/icassp49357.2023.10095802","title":"The WHU-Alibaba Audio-Visual Speaker Diarization System for the MISP 2022 Challenge","display_name":"The WHU-Alibaba Audio-Visual Speaker Diarization System for the MISP 2022 Challenge","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372338350","doi":"https://doi.org/10.1109/icassp49357.2023.10095802"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095802","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095802","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5090476096","display_name":"Ming Cheng","orcid":"https://orcid.org/0000-0002-3300-9787"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]},{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ming Cheng","raw_affiliation_strings":["Wuhan University,School of Computer Science,Wuhan,China","Data Science Research Center, Duke Kunshan University, Kunshan, China","School of Computer Science, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Data Science Research Center, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]},{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016797242","display_name":"Haoxu Wang","orcid":"https://orcid.org/0000-0002-5430-0899"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]},{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoxu Wang","raw_affiliation_strings":["Wuhan University,School of Computer Science,Wuhan,China","School of Computer Science, Wuhan University, Wuhan, China","Data Science Research Center, Duke Kunshan University, Kunshan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Data Science Research Center, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101673728","display_name":"Ziteng Wang","orcid":"https://orcid.org/0009-0001-8487-8093"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziteng Wang","raw_affiliation_strings":["Alibaba Group,China","Alibaba Group, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101992907","display_name":"Qiang Fu","orcid":"https://orcid.org/0009-0004-7159-6515"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Fu","raw_affiliation_strings":["Alibaba Group,China","Alibaba Group, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351449","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-6406-1983"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]},{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["Wuhan University,School of Computer Science,Wuhan,China","School of Computer Science, Wuhan University, Wuhan, China","Data Science Research Center, Duke Kunshan University, Kunshan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Data Science Research Center, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5090476096"],"corresponding_institution_ids":["https://openalex.org/I37461747","https://openalex.org/I4210159968"],"apc_list":null,"apc_paid":null,"fwci":1.5372,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.83171501,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"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":0.9997000098228455,"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":0.9997000098228455,"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":0.8770955801010132},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6743674278259277},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6702085137367249},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6165059208869934},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.49874162673950195},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4505418837070465},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4135037660598755},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.37531107664108276},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2202233374118805}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8770955801010132},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6743674278259277},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6702085137367249},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6165059208869934},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.49874162673950195},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4505418837070465},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4135037660598755},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.37531107664108276},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2202233374118805},{"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/icassp49357.2023.10095802","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095802","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336618","display_name":"Science and Technology Program of Suzhou","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W3212886388","https://openalex.org/W4224940398","https://openalex.org/W4297841834","https://openalex.org/W4372317224","https://openalex.org/W4375868885","https://openalex.org/W6846644525"],"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],"the":[3,7,11,22,51,55,62,67],"system":[4,41],"developed":[5],"by":[6],"WHU-Alibaba":[8],"team":[9],"for":[10],"Multimodal":[12],"Information":[13],"Based":[14],"Speech":[15],"Processing":[16,72],"(MISP)":[17],"2022":[18],"Challenge.":[19,74],"We":[20],"extend":[21],"Sequence-to-Sequence":[23],"Target-Speaker":[24],"Voice":[25],"Activity":[26],"Detection":[27],"framework":[28],"to":[29],"simultaneously":[30],"detect":[31],"multiple":[32],"speakers\u2019":[33],"voice":[34],"activities":[35],"from":[36],"audio-visual":[37],"signals.":[38],"The":[39],"final":[40],"achieves":[42],"a":[43],"diarization":[44,64],"error":[45],"rate":[46],"(DER)":[47],"of":[48,54,66],"8.82%":[49],"on":[50],"evaluation":[52],"set":[53],"competition":[56],"database,":[57],"which":[58],"ranks":[59],"1st":[60],"in":[61],"speaker":[63],"track":[65],"MISP":[68],"2022,":[69],"ICASSP":[70],"Signal":[71],"Grand":[73]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}