{"id":"https://openalex.org/W4403791928","doi":"https://doi.org/10.1145/3664647.3688980","title":"Multi-Stage Face-Voice Association Learning with Keynote Speaker Diarization","display_name":"Multi-Stage Face-Voice Association Learning with Keynote Speaker Diarization","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791928","doi":"https://doi.org/10.1145/3664647.3688980"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3688980","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3688980","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3664647.3688980","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026034735","display_name":"Ruijie Tao","orcid":"https://orcid.org/0000-0003-0021-5661"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ruijie Tao","raw_affiliation_strings":["National University of Singapore, Singapre, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-0021-5661","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapre, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056411799","display_name":"Zhan Shi","orcid":"https://orcid.org/0009-0004-9581-1996"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhan Shi","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0004-9581-1996","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111432082","display_name":"Yidi Jiang","orcid":"https://orcid.org/0000-0002-2317-9571"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yidi Jiang","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-2317-9571","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091500888","display_name":"Duc-Tuan Truong","orcid":"https://orcid.org/0009-0002-1767-7598"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Duc-Tuan Truong","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0002-1767-7598","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng-Siong Chng","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6257-7399","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052037141","display_name":"Massimo Alioto","orcid":"https://orcid.org/0000-0002-4127-8258"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Massimo Alioto","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4127-8258","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-9158-9401","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11342","last_page":"11347"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9983999729156494,"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":0.8712888956069946},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7058127522468567},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.6813040971755981},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6177975535392761},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.6025629639625549},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5818932056427002},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.45955953001976013},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38716816902160645},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3299107849597931},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2374204695224762},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1708184778690338},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.05727744102478027}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8712888956069946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7058127522468567},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.6813040971755981},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6177975535392761},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.6025629639625549},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5818932056427002},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.45955953001976013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38716816902160645},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3299107849597931},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2374204695224762},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1708184778690338},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.05727744102478027},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3688980","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3688980","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3664647.3688980","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3688980","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2963887950","https://openalex.org/W2969985801","https://openalex.org/W2979157532","https://openalex.org/W2990961119","https://openalex.org/W3016663370","https://openalex.org/W3024147341","https://openalex.org/W3024869864","https://openalex.org/W3024880099","https://openalex.org/W3025804484","https://openalex.org/W3135222947","https://openalex.org/W3139878283","https://openalex.org/W3163527109","https://openalex.org/W3171302872","https://openalex.org/W3206189675","https://openalex.org/W4224924564","https://openalex.org/W4312120960","https://openalex.org/W4372341093","https://openalex.org/W4378976870","https://openalex.org/W4387322738","https://openalex.org/W4388878581","https://openalex.org/W4392908937","https://openalex.org/W4392909895"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"The":[0],"human":[1],"brain":[2],"has":[3],"the":[4,8,32,36,63,72,94,98],"capability":[5],"to":[6,20,31,60],"associate":[7],"unknown":[9],"person's":[10],"voice":[11],"and":[12,70,76],"face":[13],"by":[14],"leveraging":[15],"their":[16],"general":[17],"relationship,":[18],"referred":[19],"as":[21],"\"cross-modal":[22],"speaker":[23,57],"verification''.":[24],"This":[25],"task":[26],"poses":[27],"significant":[28],"challenges":[29],"due":[30],"complex":[33],"relationship":[34],"between":[35],"modalities.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41],"propose":[42],"a":[43,55,82],"\"Multi-stage":[44],"Face-voice":[45,100],"Association":[46,101],"Learning":[47],"with":[48,107],"Keynote":[49],"Speaker":[50],"Diarization''(MFV-KSD)":[51],"framework.":[52],"MFV-KSD":[53,80],"contains":[54],"keynote":[56],"diarization":[58],"front-end":[59],"effectively":[61],"address":[62],"noisy":[64],"speech":[65],"inputs":[66],"issue.":[67],"To":[68],"balance":[69],"enhance":[71],"intra-modal":[73],"feature":[74],"learning":[75],"inter-modal":[77],"correlation":[78],"understanding,":[79],"utilizes":[81],"novel":[83],"three-stage":[84],"training":[85],"strategy.":[86],"Our":[87],"experimental":[88],"results":[89],"demonstrated":[90],"robust":[91],"performance,":[92],"achieving":[93],"first":[95],"rank":[96],"in":[97,102,120],"2024":[99],"Multilingual":[103],"Environments":[104],"(FAME)":[105],"challenge":[106],"an":[108],"overall":[109],"Equal":[110],"Error":[111],"Rate":[112],"(EER)":[113],"of":[114],"19.9%.":[115],"Details":[116],"can":[117],"be":[118],"found":[119],"https://github.com/TaoRuijie/MFV-KSD.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
