{"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","doi":"https://doi.org/10.1109/icassp49357.2023.10094752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094752","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2210.16127","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ming Cheng","orcid":null,"observed_orcids":[]},"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 Cheng","raw_affiliation_strings":["Wuhan University,School of Computer Science,Wuhan,China","Data Science Research Center, Duke Kunshan University, Kunshan, China","School of Computer Science, Wuhan University, Wuhan, 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":"Data Science Research Center, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]},{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100372962","display_name":"Weiqing Wang","orcid":"https://orcid.org/0000-0002-8588-7872","observed_orcids":["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","observed_orcids":["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","observed_orcids":["https://orcid.org/0000-0003-2521-8084"]},"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":"Xiaoyi Qin","raw_affiliation_strings":["Wuhan University,School of Computer Science,Wuhan,China","Data Science Research Center, Duke Kunshan University, Kunshan, China","School of Computer Science, Wuhan University, Wuhan, 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":"Data Science Research Center, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]},{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351449","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-6406-1983","observed_orcids":["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","Data Science Research Center, Duke Kunshan University, Kunshan, China","School of Computer Science, Wuhan University, Wuhan, 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":"Data Science Research Center, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]},{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5293,"has_fulltext":true,"cited_by_count":41,"citation_normalized_percentile":{"value":0.96435184,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"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":0.9639000296592712,"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":0.9639000296592712,"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":0.030899999663233757,"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/T12031","display_name":"Speech and dialogue systems","score":0.0026000000070780516,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-diarization","display_name":"speaker diarization","score":0.8759999871253967},{"id":"https://openalex.org/keywords/sequence-to-sequence-prediction","display_name":"sequence-to-sequence prediction","score":0.8420000076293945},{"id":"https://openalex.org/keywords/diarization-error-rate","display_name":"diarization error rate","score":0.8240000009536743}],"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":3,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094752","doi":"https://doi.org/10.1109/icassp49357.2023.10094752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094752","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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"},{"id":"pmh:oai:arXiv.org:2210.16127","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.16127","pdf_url":"https://arxiv.org/pdf/2210.16127","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2210.16127","doi":"https://doi.org/10.48550/arxiv.2210.16127","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2210.16127","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2210.16127","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.16127","pdf_url":"https://arxiv.org/pdf/2210.16127","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4375868885.pdf","grobid_xml":"https://content.openalex.org/works/W4375868885.grobid-xml"},"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/W2626778328","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2784874046","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2892300106","https://openalex.org/W2963745998","https://openalex.org/W2997347790","https://openalex.org/W3025260599","https://openalex.org/W3038871978","https://openalex.org/W3094325190","https://openalex.org/W3097777922","https://openalex.org/W3108962419","https://openalex.org/W3125596972","https://openalex.org/W3128688470","https://openalex.org/W3135990229","https://openalex.org/W3197980326","https://openalex.org/W3198455895","https://openalex.org/W3198858272","https://openalex.org/W4226013992","https://openalex.org/W4289656378","https://openalex.org/W4302307009","https://openalex.org/W4372259977","https://openalex.org/W6688816777","https://openalex.org/W6784256521","https://openalex.org/W6800885585","https://openalex.org/W6801496586","https://openalex.org/W6846273928"],"related_works":["https://openalex.org/W4224917363","https://openalex.org/W3025260599","https://openalex.org/W4372259977","https://openalex.org/W7155093126","https://openalex.org/W4408351832","https://openalex.org/W7155073869","https://openalex.org/W4404787841","https://openalex.org/W3195050710","https://openalex.org/W4403746899","https://openalex.org/W4416798641"],"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":10},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":6}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-05-10T00:00:00"}