{"id":"https://openalex.org/W4406859680","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849032","title":"COIN-AT-PVAD: A Conditional Intermediate Attention PVAD","display_name":"COIN-AT-PVAD: A Conditional Intermediate Attention PVAD","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406859680","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849032"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10849032","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5102549216","display_name":"En-Lun Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"En-Lun Yu","raw_affiliation_strings":["National Taiwan Normal University,Department of Computer Science and Information Engineering,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Department of Computer Science and Information Engineering,Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ruei-Xian Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I193365169","display_name":"National Chi Nan University","ror":"https://ror.org/03ha6v181","country_code":"TW","type":"education","lineage":["https://openalex.org/I193365169"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ruei-Xian Chang","raw_affiliation_strings":["National Chi Nan University,Department of Electrical Engineering,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Chi Nan University,Department of Electrical Engineering,Taiwan","institution_ids":["https://openalex.org/I193365169"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019048236","display_name":"Jeih-weih Hung","orcid":"https://orcid.org/0000-0001-9366-3070"},"institutions":[{"id":"https://openalex.org/I193365169","display_name":"National Chi Nan University","ror":"https://ror.org/03ha6v181","country_code":"TW","type":"education","lineage":["https://openalex.org/I193365169"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jeih-Weih Hung","raw_affiliation_strings":["National Chi Nan University,Department of Electrical Engineering,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Chi Nan University,Department of Electrical Engineering,Taiwan","institution_ids":["https://openalex.org/I193365169"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104352144","display_name":"Shih-Chieh Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I901624438","display_name":"Realtek (Taiwan)","ror":"https://ror.org/05x1ffr83","country_code":"TW","type":"company","lineage":["https://openalex.org/I901624438"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shih-Chieh Huang","raw_affiliation_strings":["Realtek Semiconductor Corp.,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Realtek Semiconductor Corp.,Taiwan","institution_ids":["https://openalex.org/I901624438"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047673862","display_name":"Berlin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Berlin Chen","raw_affiliation_strings":["National Taiwan Normal University,Department of Computer Science and Information Engineering,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Department of Computer Science and Information Engineering,Taiwan","institution_ids":["https://openalex.org/I134161618"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4079,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.85119922,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.767799973487854,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.767799973487854,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.7301999926567078,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10142","display_name":"Formal Methods in Verification","score":0.6771000027656555,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.5136784911155701}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5136784911155701}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10849032","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":22,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1999454387","https://openalex.org/W2034940213","https://openalex.org/W2617258110","https://openalex.org/W2625979394","https://openalex.org/W2742061524","https://openalex.org/W2760103357","https://openalex.org/W3015383801","https://openalex.org/W3024085360","https://openalex.org/W3025260599","https://openalex.org/W3120769709","https://openalex.org/W3143923103","https://openalex.org/W3195050710","https://openalex.org/W3198453247","https://openalex.org/W4223655162","https://openalex.org/W4392904540","https://openalex.org/W4392908983","https://openalex.org/W4402112224","https://openalex.org/W6631190155","https://openalex.org/W6751420435","https://openalex.org/W6766978945","https://openalex.org/W6869928541"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Personalized":[0],"voice":[1],"activity":[2],"detection":[3],"(PVAD),":[4],"compared":[5,115],"to":[6,34,60,81,116],"conventional":[7],"VAD,":[8],"shows":[9],"more":[10],"developmental":[11],"potential":[12],"in":[13,136],"scenarios":[14],"with":[15],"multiple":[16],"speaker":[17,25,40,45],"interference.":[18],"Among":[19],"the":[20,35,68,75,97],"various":[21,88],"methods":[22],"for":[23],"integrating":[24],"and":[26,73,125],"acoustic":[27],"features,":[28],"performance":[29],"may":[30],"be":[31],"limited":[32,106],"due":[33],"weaker":[36],"representational":[37,107],"capability":[38],"of":[39],"embeddings":[41],"derived":[42],"from":[43],"external":[44,102],"verification":[46],"models.":[47],"This":[48,64],"study":[49],"proposes":[50],"a":[51,129],"new":[52],"architecture":[53,65],"called":[54],"Conditional":[55],"Intermediate":[56],"Attention":[57],"PVAD":[58],"(COIN-AT-PVAD)":[59],"address":[61],"this":[62],"issue.":[63],"builds":[66],"upon":[67],"Attentive":[69],"Score":[70],"(AS)":[71],"module":[72],"incorporates":[74],"Feature-wise":[76],"Linear":[77],"Modulation":[78],"(FiLM)":[79],"scheme":[80],"better":[82],"integrate":[83],"multimodal":[84],"information.":[85],"Through":[86],"comparing":[87],"fusion":[89],"strategies,":[90],"we":[91],"show":[92],"that":[93],"COIN-AT-PVAD":[94,120],"significantly":[95],"surpasses":[96],"baseline":[98],"model,":[99],"especially":[100],"when":[101,114],"embedding":[103],"features":[104],"have":[105],"capacity.":[108],"Experimental":[109],"findings":[110],"also":[111],"indicate":[112],"that,":[113],"some":[117],"state-of-the-art":[118],"models,":[119],"achieves":[121],"superior":[122],"average":[123],"precision":[124],"accuracy":[126],"while":[127],"retaining":[128],"compact":[130],"model":[131],"size,":[132],"showcasing":[133],"its":[134],"efficacy":[135],"real-world":[137],"applications":[138],"on":[139],"resource-limited":[140],"devices.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}