{"id":"https://openalex.org/W4408351832","doi":"https://doi.org/10.1109/icassp49660.2025.10890295","title":"Flow-TSVAD: Target-Speaker Voice Activity Detection via Latent Flow Matching for Speaker Diarization","display_name":"Flow-TSVAD: Target-Speaker Voice Activity Detection via Latent Flow Matching for Speaker Diarization","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408351832","doi":"https://doi.org/10.1109/icassp49660.2025.10890295"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5101416769","display_name":"Zhengyang Chen","orcid":"https://orcid.org/0000-0003-1293-8146"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengyang Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086824490","display_name":"Bing Han","orcid":"https://orcid.org/0000-0003-4584-1092"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Han","raw_affiliation_strings":["Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328259","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0002-0288-4212"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["Shenzhen Research Institute of Big Data,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data,Shenzhen,China","institution_ids":["https://openalex.org/I4210099586"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]}],"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":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9950000047683716,"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":0.9950000047683716,"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":0.9377999901771545,"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/T10860","display_name":"Speech and Audio Processing","score":0.9115999937057495,"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":0.8229197859764099},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.712790846824646},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7032783031463623},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6236652135848999},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.48795098066329956},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.4393099248409271},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.41917166113853455},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34360283613204956}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8229197859764099},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.712790846824646},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7032783031463623},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6236652135848999},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.48795098066329956},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.4393099248409271},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.41917166113853455},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34360283613204956},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W123007118","https://openalex.org/W2159591770","https://openalex.org/W2168025753","https://openalex.org/W2603777577","https://openalex.org/W2808631503","https://openalex.org/W2963470929","https://openalex.org/W2972949456","https://openalex.org/W3007946293","https://openalex.org/W3008357631","https://openalex.org/W3025260599","https://openalex.org/W3097777922","https://openalex.org/W3140898556","https://openalex.org/W3178462146","https://openalex.org/W4220731890","https://openalex.org/W4252812408","https://openalex.org/W4297841362","https://openalex.org/W4297841790","https://openalex.org/W4313316127","https://openalex.org/W4372340947","https://openalex.org/W4375868885","https://openalex.org/W4380434618","https://openalex.org/W4385245566","https://openalex.org/W4385822449","https://openalex.org/W4385822749","https://openalex.org/W4390873752","https://openalex.org/W4391892525","https://openalex.org/W4392931179","https://openalex.org/W4402111455","https://openalex.org/W4405022263","https://openalex.org/W6769178842","https://openalex.org/W6846539466","https://openalex.org/W6860952413"],"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/W4406496871","https://openalex.org/W1521049138","https://openalex.org/W2023466863"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,15,53,142,165],"is":[2,75],"typically":[3],"considered":[4],"as":[5,133],"a":[6,38,89,134],"discriminative":[7,10],"task,":[8],"using":[9],"approaches":[11],"to":[12,64,128],"produce":[13],"fixed":[14],"results.":[16,131],"In":[17],"this":[18,79],"paper,":[19],"we":[20,81,111],"explore":[21],"for":[22,33,139],"the":[23,26,45,60,65,72,84,95,106,114,120,146,151,155,164],"first":[24],"time":[25],"use":[27],"of":[28,71],"neural":[29],"network-based":[30],"generative":[31,42,61,96,135],"methods":[32],"speaker":[34,48],"diarization.":[35],"We":[36],"implement":[37],"Flow-Matching":[39],"(FM)":[40],"based":[41],"algorithm":[43,116],"within":[44],"sequenceto-sequence":[46],"target":[47],"voice":[49],"activity":[50],"detection":[51],"(Seq2Seq-TSVAD)":[52],"system.":[54,109],"Our":[55],"experiments":[56],"reveal":[57],"that":[58,113],"applying":[59,94],"method":[62,102],"directly":[63],"original":[66],"binary":[67,85],"label":[68,86],"sequence":[69,87],"space":[70,92],"TS-VAD":[73],"output":[74],"ineffective.":[76],"To":[77],"address":[78],"issue,":[80],"propose":[82],"mapping":[83],"into":[88],"dense":[90],"latent":[91],"before":[93],"algorithm,":[97],"and":[98],"our":[99],"proposed":[100],"Flow-TSVAD":[101,137],"can":[103,161],"significantly":[104],"outperform":[105],"traditional":[107],"Seq2Seq-TSVAD":[108],"Additionally,":[110],"observe":[112],"FM":[115],"converges":[117],"rapidly":[118],"during":[119],"inference":[121,126],"stage,":[122],"only":[123],"requiring":[124],"two":[125],"steps":[127],"achieve":[129],"promising":[130],"Moreover,":[132],"model,":[136],"allows":[138],"sampling":[140,159],"different":[141],"results":[143,156],"by":[144],"running":[145],"model":[147],"multiple":[148],"times,":[149],"so":[150],"ensemble":[152],"system":[153],"combining":[154],"from":[157],"various":[158],"instances":[160],"further":[162],"boost":[163],"performance.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}