{"id":"https://openalex.org/W4372259977","doi":"https://doi.org/10.1109/icassp49357.2023.10095185","title":"Target Speaker Voice Activity Detection with Transformers and Its Integration with End-To-End Neural Diarization","display_name":"Target Speaker Voice Activity Detection with Transformers and Its Integration with End-To-End Neural Diarization","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372259977","doi":"https://doi.org/10.1109/icassp49357.2023.10095185"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095185","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095185","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":"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, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, 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, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, 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, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, 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, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, 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, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, 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":26,"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":0.9998999834060669,"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":0.9991000294685364,"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":0.786389946937561},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6818782091140747},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6804061532020569},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6471285820007324},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5559183955192566},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5223592519760132},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5020771026611328},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28193798661231995},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.250111848115921},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16060742735862732},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.07645243406295776}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.786389946937561},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6818782091140747},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6804061532020569},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6471285820007324},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5559183955192566},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5223592519760132},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5020771026611328},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28193798661231995},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.250111848115921},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16060742735862732},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.07645243406295776},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095185","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095185","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W2150769028","https://openalex.org/W2219249508","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2726515241","https://openalex.org/W2734774145","https://openalex.org/W2808631503","https://openalex.org/W2962715207","https://openalex.org/W2972949456","https://openalex.org/W2999547272","https://openalex.org/W3008357631","https://openalex.org/W3015780472","https://openalex.org/W3020336359","https://openalex.org/W3025260599","https://openalex.org/W3038871978","https://openalex.org/W3095212884","https://openalex.org/W3111481301","https://openalex.org/W3135990229","https://openalex.org/W3142516134","https://openalex.org/W3162347631","https://openalex.org/W3163903701","https://openalex.org/W3182885906","https://openalex.org/W3196857193","https://openalex.org/W3198455895","https://openalex.org/W3198858272","https://openalex.org/W3209984917","https://openalex.org/W3212886388","https://openalex.org/W4220731890","https://openalex.org/W4221155598","https://openalex.org/W4221167533","https://openalex.org/W4225661121","https://openalex.org/W4237168004","https://openalex.org/W4283014282","https://openalex.org/W4372259977","https://openalex.org/W4385245566","https://openalex.org/W6682600690","https://openalex.org/W6688816777","https://openalex.org/W6739901393","https://openalex.org/W6787439801","https://openalex.org/W6791480293","https://openalex.org/W6798708994","https://openalex.org/W6800885585","https://openalex.org/W6801496586","https://openalex.org/W6809668307","https://openalex.org/W6810252181","https://openalex.org/W6842214994"],"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":{"This":[0],"paper":[1],"describes":[2],"a":[3,102,150,175,180,187],"speaker":[4,10,46,54,67,119],"diarization":[5,103,109,141],"model":[6,36,59,104,177],"based":[7,105,112],"on":[8,106,128,165],"target":[9],"voice":[11],"activity":[12],"detection":[13,120],"(TS-VAD)":[14],"using":[15,132],"transformers.":[16],"To":[17],"overcome":[18],"the":[19,53,58,63,66,71,86,92,123,133,136,140,166,171],"original":[20,172],"TS-VAD":[21,72,146],"model\u2019s":[22],"drawback":[23],"of":[24,32,65,91,145,155,184],"being":[25],"unable":[26],"to":[27,52,56,62,70,84,96,170],"handle":[28],"an":[29],"arbitrary":[30],"number":[31],"speakers,":[33],"we":[34],"investigate":[35],"architectures":[37],"that":[38,131],"use":[39],"input":[40,93],"tensors":[41],"with":[42,110,122,174],"variable-length":[43],"time":[44],"and":[45,88],"dimensions.":[47],"Transformer":[48],"layers":[49,76,83],"are":[50,77],"applied":[51],"axis":[55],"make":[57],"output":[60],"insensitive":[61],"order":[64],"profiles":[68],"provided":[69],"model.":[73],"Time-wise":[74],"sequential":[75],"interspersed":[78],"between":[79],"these":[80],"speaker-wise":[81],"transformer":[82],"allow":[85],"temporal":[87],"cross-speaker":[89,137],"correlations":[90],"speech":[94],"signal":[95],"be":[97],"captured.":[98],"We":[99],"also":[100],"extend":[101],"end-to-end":[107],"neural":[108],"encoder-decoder":[111],"attractors":[113],"(EEND-EDA)":[114],"by":[115,147,163],"replacing":[116],"its":[117],"dot-product-based":[118],"layer":[121],"transformer-based":[124],"TS-VAD.":[125],"Experimental":[126],"results":[127],"VoxConverse":[129],"show":[130],"transformers":[134],"for":[135],"modeling":[138],"reduces":[139,161],"error":[142],"rate":[143],"(DER)":[144],"11.3%,":[148],"achieving":[149,179],"new":[151,181],"state-of-the-art":[152],"(SOTA)":[153],"DER":[154,162,183],"4.57%.":[156],"Also,":[157],"our":[158],"extended":[159],"EEND-EDA":[160,173],"6.9%":[164],"CALLHOME":[167],"dataset":[168],"relative":[169],"similar":[176],"size,":[178],"SOTA":[182],"11.18%":[185],"under":[186],"widely":[188],"used":[189],"training":[190],"data":[191],"setting.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
