{"id":"https://openalex.org/W4392904540","doi":"https://doi.org/10.1109/icassp48485.2024.10446581","title":"AS-pVAD: A Frame-Wise Personalized Voice Activity Detection Network with Attentive Score Loss","display_name":"AS-pVAD: A Frame-Wise Personalized Voice Activity Detection Network with Attentive Score Loss","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904540","doi":"https://doi.org/10.1109/icassp48485.2024.10446581"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446581","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":"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/A5088943805","display_name":"Fen-Ting Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fenting Liu","raw_affiliation_strings":["Alibaba Group,Hummingbird Audio Lab,Hangzhou,China","College of Information Science & Electronic Engineering, Zhejiang University, Hangzhou, China","Hummingbird Audio Lab, Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hummingbird Audio Lab,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"College of Information Science & Electronic Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Hummingbird Audio Lab, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011297325","display_name":"Feifei Xiong","orcid":"https://orcid.org/0000-0001-9783-2169"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feifei Xiong","raw_affiliation_strings":["Alibaba Group,Hummingbird Audio Lab,Hangzhou,China","Hummingbird Audio Lab, Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hummingbird Audio Lab,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Hummingbird Audio Lab, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007703197","display_name":"Yiya Hao","orcid":"https://orcid.org/0000-0003-1234-4209"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiya Hao","raw_affiliation_strings":["Alibaba Group,Hummingbird Audio Lab,Hangzhou,China","Hummingbird Audio Lab, Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hummingbird Audio Lab,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Hummingbird Audio Lab, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050521239","display_name":"Kechenying Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kechenying Zhou","raw_affiliation_strings":["Alibaba Group,Hummingbird Audio Lab,Hangzhou,China","Hummingbird Audio Lab, Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hummingbird Audio Lab,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Hummingbird Audio Lab, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082488018","display_name":"Chenhui Zhang","orcid":"https://orcid.org/0000-0002-0124-6315"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenhui Zhang","raw_affiliation_strings":["Zhejiang University,College of Information Science & Electronic Engineering,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Information Science & Electronic Engineering,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101628650","display_name":"Jinwei Feng","orcid":"https://orcid.org/0009-0000-2516-3891"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinwei Feng","raw_affiliation_strings":["Alibaba Group,Hummingbird Audio Lab,Hangzhou,China","Hummingbird Audio Lab, Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hummingbird Audio Lab,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Hummingbird Audio Lab, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7515,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.90820923,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"11476","last_page":"11480"},"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":0.9987000226974487,"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/embedding","display_name":"Embedding","score":0.6829953193664551},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.677237868309021},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.667658269405365},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.631176769733429},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5408937931060791},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5222431421279907},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.509128987789154},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4362652599811554},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.43475541472435},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3610100746154785},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11797842383384705}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6829953193664551},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.677237868309021},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.667658269405365},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.631176769733429},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5408937931060791},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5222431421279907},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.509128987789154},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4362652599811554},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.43475541472435},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3610100746154785},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11797842383384705},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446581","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W182487737","https://openalex.org/W1494198834","https://openalex.org/W1974387177","https://openalex.org/W2099145922","https://openalex.org/W2149053750","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2240641835","https://openalex.org/W2410879554","https://openalex.org/W2535438430","https://openalex.org/W2603947633","https://openalex.org/W2794506738","https://openalex.org/W2805466703","https://openalex.org/W2885307078","https://openalex.org/W2936299888","https://openalex.org/W2937484199","https://openalex.org/W2954930777","https://openalex.org/W2963868408","https://openalex.org/W2969985801","https://openalex.org/W3010925296","https://openalex.org/W3024085360","https://openalex.org/W3024869864","https://openalex.org/W3025260599","https://openalex.org/W3142516134","https://openalex.org/W3160747466","https://openalex.org/W3198453247","https://openalex.org/W3198533616","https://openalex.org/W4223655162","https://openalex.org/W4224917363","https://openalex.org/W4224919629","https://openalex.org/W4225905067","https://openalex.org/W4296068967","https://openalex.org/W4297841423","https://openalex.org/W4372346434","https://openalex.org/W4372349226","https://openalex.org/W6691726237"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W2373577936","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,27,34,69,93],"lightweight":[3,35],"neural":[4],"network":[5],"with":[6,26,68],"attentive":[7,46],"score":[8,47],"loss":[9,48],"for":[10,58],"frame-wise":[11],"personalized":[12],"voice":[13],"activity":[14],"detection":[15],"(i.e.,":[16],"AS-pVAD).":[17],"Instead":[18],"of":[19,30,108],"using":[20],"an":[21],"external":[22],"speaker":[23,42,81],"embedding":[24,56,63],"extractor":[25],"large":[28],"number":[29],"parameters,":[31],"AS-pVAD":[32,72,104],"employs":[33],"internal":[36],"model":[37],"to":[38,52,61,77,90,129,132],"extract":[39],"the":[40,79,83,97,130,134],"target":[41,80],"embedding.":[43],"A":[44],"novel":[45],"constraint":[49],"is":[50,88,125],"proposed":[51],"better":[53],"exploit":[54],"such":[55],"clues":[57],"pVAD":[59],"compared":[60],"conventional":[62],"concatenation.":[64],"Through":[65],"joint":[66],"training":[67],"regular":[70,94],"VAD,":[71],"can":[73],"be":[74],"further":[75],"improved":[76],"identify":[78],"in":[82,96,112,136],"enrollment":[84],"cases":[85],"while":[86],"it":[87],"able":[89],"function":[91],"as":[92],"VAD":[95],"enrollment-less":[98],"cases.":[99],"Experimental":[100],"results":[101],"show":[102],"that":[103],"achieves":[105],"over":[106],"0.9":[107],"AUCROC":[109],"on":[110],"average":[111],"two-speaker":[113],"talking":[114],"scenario":[115],"under":[116],"various":[117],"noisy":[118],"and":[119],"reverberant":[120],"environments.":[121],"Our":[122],"test":[123],"set":[124],"also":[126],"publicly":[127],"released":[128],"community":[131],"facilitate":[133],"research":[135],"this":[137],"area.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}