{"id":"https://openalex.org/W4392903962","doi":"https://doi.org/10.1109/icassp48485.2024.10446475","title":"Profile-Error-Tolerant Target-Speaker Voice Activity Detection","display_name":"Profile-Error-Tolerant Target-Speaker Voice Activity Detection","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903962","doi":"https://doi.org/10.1109/icassp48485.2024.10446475"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446475","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446475","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5100408281","display_name":"Dongmei Wang","orcid":"https://orcid.org/0000-0002-6930-0066"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongmei Wang","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101602536","display_name":"Xiong Xiao","orcid":"https://orcid.org/0009-0001-5128-6518"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiong Xiao","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016279564","display_name":"Naoyuki Kanda","orcid":"https://orcid.org/0000-0002-8628-3288"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naoyuki Kanda","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112853229","display_name":"Midia Yousefi","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Midia Yousefi","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101674460","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0002-3101-7011"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Wu","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11906","last_page":"11910"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9997000098228455,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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":0.8425053358078003},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7808484435081482},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7101656198501587},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6669220924377441},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6483458876609802},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.534170925617218},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5020895004272461},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.43853792548179626},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3849729001522064},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31887632608413696},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2695508897304535}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8425053358078003},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7808484435081482},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7101656198501587},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6669220924377441},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6483458876609802},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.534170925617218},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5020895004272461},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.43853792548179626},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3849729001522064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31887632608413696},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2695508897304535},{"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/icassp48485.2024.10446475","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446475","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/10","score":0.6499999761581421,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1558276682","https://openalex.org/W1607302042","https://openalex.org/W1965819578","https://openalex.org/W2038101708","https://openalex.org/W2222512263","https://openalex.org/W2460742184","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2889418727","https://openalex.org/W2972949456","https://openalex.org/W2981103786","https://openalex.org/W2997419692","https://openalex.org/W2999547272","https://openalex.org/W3008357631","https://openalex.org/W3015463733","https://openalex.org/W3015780472","https://openalex.org/W3020336359","https://openalex.org/W3025260599","https://openalex.org/W3038871978","https://openalex.org/W3095212884","https://openalex.org/W3105031100","https://openalex.org/W3111481301","https://openalex.org/W3142516134","https://openalex.org/W3162347631","https://openalex.org/W3197331597","https://openalex.org/W3197980326","https://openalex.org/W3198455895","https://openalex.org/W3198858272","https://openalex.org/W3212886388","https://openalex.org/W4220731890","https://openalex.org/W4221155598","https://openalex.org/W4221167533","https://openalex.org/W4237168004","https://openalex.org/W4372259977","https://openalex.org/W4375868885","https://openalex.org/W6768584815","https://openalex.org/W6787439801","https://openalex.org/W6800885585","https://openalex.org/W6801496586","https://openalex.org/W6802591457","https://openalex.org/W6809668307","https://openalex.org/W6810252181"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W2149220986","https://openalex.org/W1521299571","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"Target-Speaker":[0],"Voice":[1],"Activity":[2],"Detection":[3],"(TS-VAD)":[4],"utilizes":[5],"a":[6,46,85,93],"set":[7,94],"of":[8,88,95],"speaker":[9,18,36,72,112,131],"profiles":[10,40,98,113],"alongside":[11],"an":[12,58],"input":[13,53],"audio":[14],"signal":[15],"to":[16,60,70,99,120],"perform":[17],"diarization.":[19,107],"While":[20],"its":[21],"superiority":[22],"over":[23,51],"conventional":[24],"methods":[25],"has":[26],"been":[27],"demonstrated,":[28],"the":[29,52,104,122,125,140,146],"method":[30,50,143],"can":[31,83],"suffer":[32],"from":[33],"errors":[34],"in":[35],"profiles,":[37],"as":[38],"those":[39],"are":[41],"typically":[42],"obtained":[43],"by":[44,78,115],"running":[45],"traditional":[47],"clustering-based":[48],"diarization":[49],"signal.":[54],"This":[55,75],"paper":[56],"proposes":[57],"extension":[59],"TS-VAD,":[61],"called":[62],"Profile-Error-Tolerant":[63],"TS-":[64],"VAD":[65],"(PETTSVAD),":[66],"which":[67],"is":[68,76],"robust":[69],"such":[71],"profile":[73],"errors.":[74],"achieved":[77],"employing":[79],"transformer-based":[80],"TS-VAD":[81,142],"that":[82,136],"handle":[84,100],"variable":[86],"number":[87],"speakers":[89,101],"and":[90,127,148],"further":[91],"introducing":[92],"additional":[96],"pseudo-speaker":[97],"undetected":[102],"during":[103],"first":[105],"pass":[106],"During":[108],"training,":[109],"we":[110],"use":[111],"estimated":[114],"multiple":[116],"different":[117],"clustering":[118],"algorithms":[119],"reduce":[121],"mismatch":[123],"between":[124],"training":[126],"testing":[128],"conditions":[129],"regarding":[130],"profiles.":[132],"Experimental":[133],"results":[134],"show":[135],"PET-TSVAD":[137],"consistently":[138],"outperforms":[139],"existing":[141],"on":[144],"both":[145],"VoxConverse":[147],"DIHARD-I":[149],"datasets.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}