{"id":"https://openalex.org/W4375868885","doi":"https://doi.org/10.1109/icassp49357.2023.10094752","title":"Target-Speaker Voice Activity Detection Via Sequence-to-Sequence Prediction","display_name":"Target-Speaker Voice Activity Detection Via Sequence-to-Sequence Prediction","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868885","doi":"https://doi.org/10.1109/icassp49357.2023.10094752"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094752","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/A5035358464","display_name":"Ming Cheng","orcid":"https://orcid.org/0000-0002-3466-234X"},"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","School of Computer Science, Wuhan University, Wuhan, China","Data Science Research Center, Duke Kunshan University, Kunshan, China"],"raw_orcid":null,"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/A5100372962","display_name":"Weiqing Wang","orcid":"https://orcid.org/0000-0002-8588-7872"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiqing Wang","raw_affiliation_strings":["Duke Kunshan University,Data Science Research Center,Kunshan,China","Data Science Research Center, Duke Kunshan University, Kunshan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,Data Science Research Center,Kunshan,China","institution_ids":["https://openalex.org/I4210159968"]},{"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/A5103133240","display_name":"Yucong Zhang","orcid":"https://orcid.org/0000-0001-6723-7326"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yucong Zhang","raw_affiliation_strings":["Duke Kunshan University,Data Science Research Center,Kunshan,China","Data Science Research Center, Duke Kunshan University, Kunshan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,Data Science Research Center,Kunshan,China","institution_ids":["https://openalex.org/I4210159968"]},{"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/A5075605099","display_name":"Xiaoyi Qin","orcid":"https://orcid.org/0000-0003-2521-8084"},"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":"Xiaoyi Qin","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"],"raw_orcid":null,"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":"last","author":{"id":"https://openalex.org/A5100351449","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-6406-1983"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"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"]}],"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"],"raw_orcid":null,"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/A5035358464"],"corresponding_institution_ids":["https://openalex.org/I37461747","https://openalex.org/I4210159968"],"apc_list":null,"apc_paid":null,"fwci":6.3971,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.97558709,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"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/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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.7762296199798584},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7736286520957947},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7575832009315491},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6586074829101562},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6225131154060364},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5952088236808777},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5773259401321411},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5584890246391296},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.47742733359336853},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4606277048587799},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.353441059589386},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3397552967071533},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2331790328025818},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09042045474052429}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7762296199798584},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7736286520957947},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7575832009315491},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6586074829101562},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6225131154060364},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5952088236808777},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5773259401321411},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5584890246391296},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.47742733359336853},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4606277048587799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.353441059589386},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3397552967071533},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2331790328025818},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09042045474052429},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094752","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":[],"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2121812409","https://openalex.org/W2159591770","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2892300106","https://openalex.org/W2963745998","https://openalex.org/W2969985801","https://openalex.org/W3025260599","https://openalex.org/W3038871978","https://openalex.org/W3094325190","https://openalex.org/W3097777922","https://openalex.org/W3128688470","https://openalex.org/W3196595845","https://openalex.org/W3197980326","https://openalex.org/W3198455895","https://openalex.org/W3198858272","https://openalex.org/W3212886388","https://openalex.org/W4289656378","https://openalex.org/W4302307009","https://openalex.org/W4372259977","https://openalex.org/W4385245566","https://openalex.org/W6688816777","https://openalex.org/W6772381481","https://openalex.org/W6784256521","https://openalex.org/W6790297703","https://openalex.org/W6800885585","https://openalex.org/W6801496586","https://openalex.org/W6811230874","https://openalex.org/W6846273928"],"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":{"Target-speaker":[0],"voice":[1,41],"activity":[2],"detection":[3],"is":[4],"currently":[5],"a":[6,19],"promising":[7],"approach":[8],"for":[9],"speaker":[10,48],"diarization":[11,58],"in":[12],"complex":[13],"acoustic":[14],"environments.":[15],"This":[16],"paper":[17],"presents":[18],"novel":[20],"Sequence-to-Sequence":[21],"Target-Speaker":[22],"Voice":[23],"Activity":[24],"Detection":[25],"(Seq2Seq-TSVAD)":[26],"method":[27],"that":[28,46],"can":[29,54],"efficiently":[30],"address":[31],"the":[32,57,64,71,81,86],"joint":[33],"modeling":[34],"of":[35,68,80],"large-scale":[36],"speakers":[37],"and":[38,50,75],"predict":[39],"high-resolution":[40],"activities.":[42],"Experimental":[43],"results":[44],"show":[45],"larger":[47],"capacity":[49],"higher":[51],"output":[52],"resolution":[53],"significantly":[55],"reduce":[56],"error":[59],"rate":[60],"(DER),":[61],"which":[62],"achieves":[63],"new":[65],"state-of-the-art":[66],"performance":[67],"4.55%":[69],"on":[70,77],"VoxConverse":[72],"test":[73],"set":[74,84],"10.77%":[76],"Track":[78],"1":[79],"DIHARD-III":[82],"evaluation":[83,88],"under":[85],"widely-used":[87],"metrics.":[89]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":5}],"updated_date":"2026-05-18T08:16:58.900851","created_date":"2025-10-10T00:00:00"}
