{"id":"https://openalex.org/W3007432863","doi":"https://doi.org/10.1109/isspit47144.2019.9001869","title":"A Fusion Model for Robust Voice Activity Detection","display_name":"A Fusion Model for Robust Voice Activity Detection","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3007432863","doi":"https://doi.org/10.1109/isspit47144.2019.9001869","mag":"3007432863"},"language":"en","primary_location":{"id":"doi:10.1109/isspit47144.2019.9001869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isspit47144.2019.9001869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)","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/A5046540992","display_name":"Guan-Bo Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guan-Bo Wang","raw_affiliation_strings":["Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100692904","display_name":"Wei-Qiang Zhang","orcid":"https://orcid.org/0000-0003-3841-1959"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Qiang Zhang","raw_affiliation_strings":["Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5046540992"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.8293,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74677796,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"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":0.9997000098228455,"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":0.9997000098228455,"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":0.6149175763130188},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5118891000747681},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4984710216522217},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.41377902030944824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29965266585350037},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0949603021144867}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6149175763130188},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5118891000747681},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4984710216522217},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.41377902030944824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29965266585350037},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0949603021144867},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isspit47144.2019.9001869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isspit47144.2019.9001869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.550000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W1985242443","https://openalex.org/W2032362923","https://openalex.org/W2044893557","https://openalex.org/W2103635001","https://openalex.org/W2116520137","https://openalex.org/W2149053750","https://openalex.org/W2170088868","https://openalex.org/W2806318065","https://openalex.org/W2917987043","https://openalex.org/W2922122886","https://openalex.org/W2928746352","https://openalex.org/W2949117887","https://openalex.org/W2964121744","https://openalex.org/W3010659501","https://openalex.org/W4254642886","https://openalex.org/W6752435643"],"related_works":["https://openalex.org/W2132659060","https://openalex.org/W2893763841","https://openalex.org/W2368779261","https://openalex.org/W2794438528","https://openalex.org/W2778699561","https://openalex.org/W2995996972","https://openalex.org/W2312116756","https://openalex.org/W3128571556","https://openalex.org/W2353265673","https://openalex.org/W2034174504"],"abstract_inverted_index":{"As":[0],"an":[1],"indispensable":[2],"front-end":[3],"system,":[4,99],"it":[5],"is":[6,37],"crucial":[7],"for":[8,62,83],"voice":[9],"activity":[10],"detection":[11],"(VAD)":[12],"system":[13,41,51,102],"to":[14,39,96],"be":[15],"robust":[16],"in":[17,43,112],"all":[18,113],"kinds":[19],"of":[20,55,77,91],"conditions.":[21],"In":[22],"this":[23],"paper,":[24],"we":[25],"propose":[26],"a":[27],"fusion":[28,93],"model":[29],"based":[30],"VAD":[31,84],"system.":[32],"A":[33],"supervised":[34],"fusing":[35],"strategy":[36],"introduced":[38],"improve":[40],"performance":[42,105],"diverse":[44],"data":[45],"domains.":[46],"We":[47],"evaluate":[48],"our":[49,92,100],"proposed":[50,101],"on":[52],"development":[53],"datasets":[54],"Public":[56],"Safety":[57],"Communications":[58],"(PSC),":[59],"Video":[60],"Annotation":[61],"Speech":[63,71],"Technologies":[64,73],"(VAST)":[65],"and":[66],"Babel":[67],"from":[68],"NIST":[69],"Open":[70],"Analytic":[72],"2019":[74],"(OpenSAT19),":[75],"each":[76],"which":[78],"has":[79],"its":[80],"own":[81],"challenges":[82],"systems.":[85],"Experimental":[86],"results":[87],"show":[88],"the":[89,97,107],"robustness":[90],"model.":[94],"Compared":[95],"baseline":[98],"achieves":[103],"better":[104],"under":[106],"OpenSAT19":[108],"official":[109],"evaluation":[110],"metrics":[111],"three":[114],"datasets.":[115]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
