{"id":"https://openalex.org/W2126693545","doi":"https://doi.org/10.1109/tasl.2010.2052803","title":"Robust Voice Activity Detection Using Long-Term Signal Variability","display_name":"Robust Voice Activity Detection Using Long-Term Signal Variability","publication_year":2010,"publication_date":"2010-06-18","ids":{"openalex":"https://openalex.org/W2126693545","doi":"https://doi.org/10.1109/tasl.2010.2052803","mag":"2126693545"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2010.2052803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2052803","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5046000500","display_name":"Prasanta Ghosh","orcid":"https://orcid.org/0000-0002-2925-1802"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Prasanta Kumar Ghosh","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory, Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","Dept. of Electr. Eng. Univ. of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Dept. of Electr. Eng. Univ. of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072740718","display_name":"Andreas Tsiartas","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Tsiartas","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory, Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","Dept. of Electr. Eng. Univ. of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Dept. of Electr. Eng. Univ. of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory, Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","Dept. of Electr. Eng. Univ. of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Dept. of Electr. Eng. Univ. of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046000500"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":11.7998,"has_fulltext":false,"cited_by_count":175,"citation_normalized_percentile":{"value":0.99072753,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"19","issue":"3","first_page":"600","last_page":"613"},"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7661224603652954},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6454665660858154},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6326035857200623},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.58458012342453},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5826789140701294},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5629521608352661},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5535467863082886},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5027713775634766},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48438626527786255},{"id":"https://openalex.org/keywords/detection-theory","display_name":"Detection theory","score":0.4597492516040802},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4523315727710724},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4326792061328888},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.4115108251571655},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.324387788772583},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2568330764770508},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20431318879127502},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11261218786239624},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.0942525863647461},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.05937734246253967},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.04896342754364014}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7661224603652954},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6454665660858154},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6326035857200623},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.58458012342453},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5826789140701294},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5629521608352661},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5535467863082886},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5027713775634766},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48438626527786255},{"id":"https://openalex.org/C137270730","wikidata":"https://www.wikidata.org/wiki/Q120811","display_name":"Detection theory","level":3,"score":0.4597492516040802},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4523315727710724},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4326792061328888},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.4115108251571655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.324387788772583},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2568330764770508},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20431318879127502},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11261218786239624},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.0942525863647461},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.05937734246253967},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.04896342754364014},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2010.2052803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2052803","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6600000262260437,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1501620","https://openalex.org/W175094223","https://openalex.org/W304112886","https://openalex.org/W1487022053","https://openalex.org/W1521990686","https://openalex.org/W1584270973","https://openalex.org/W1598897937","https://openalex.org/W1673191017","https://openalex.org/W1784695092","https://openalex.org/W1897045322","https://openalex.org/W1905983571","https://openalex.org/W1974387177","https://openalex.org/W1993911116","https://openalex.org/W2003662252","https://openalex.org/W2023684629","https://openalex.org/W2099111195","https://openalex.org/W2115717467","https://openalex.org/W2117468249","https://openalex.org/W2119393553","https://openalex.org/W2119564743","https://openalex.org/W2120353785","https://openalex.org/W2128625680","https://openalex.org/W2129120544","https://openalex.org/W2135445137","https://openalex.org/W2139415621","https://openalex.org/W2152395643","https://openalex.org/W2164715564","https://openalex.org/W2171748469","https://openalex.org/W2476623277","https://openalex.org/W2541377018","https://openalex.org/W3127686677","https://openalex.org/W3146874108","https://openalex.org/W4205897042","https://openalex.org/W6607049298","https://openalex.org/W6677758613","https://openalex.org/W6729274634"],"related_works":["https://openalex.org/W2387156362","https://openalex.org/W2074073404","https://openalex.org/W2036807298","https://openalex.org/W1990370133","https://openalex.org/W2773794959","https://openalex.org/W4285814784","https://openalex.org/W1965055812","https://openalex.org/W2093613770","https://openalex.org/W2072903707","https://openalex.org/W4290996275"],"abstract_inverted_index":{"We":[0,18,69,130],"propose":[1],"a":[2,61],"novel":[3],"long-term":[4],"signal":[5,54],"variability":[6],"(LTSV)":[7],"measure,":[8],"which":[9],"describes":[10],"the":[11,16,20,37,42,99,102,121,124,138,144,149,162,166,169,181],"degree":[12],"of":[13,15,82,87,101,140,168,180],"nonstationarity":[14],"signal.":[17],"analyze":[19],"LTSV":[21,43,170],"measure":[22,44],"both":[23],"analytically":[24],"and":[25,29,32,75,84,110,148,156],"empirically":[26],"for":[27,64,172,178],"speech":[28,53],"various":[30],"stationary":[31],"nonstationary":[33],"noises.":[34],"Based":[35],"on":[36],"analysis,":[38],"we":[39],"find":[40,132],"that":[41,98,118],"can":[45,57],"be":[46,58],"used":[47,59],"to":[48],"discriminate":[49],"noise":[50],"from":[51],"noisy":[52],"and,":[55],"hence,":[56],"as":[60],"potential":[62],"feature":[63,171],"voice":[65],"activity":[66],"detection":[67],"(VAD).":[68],"describe":[70],"an":[71],"LTSV-based":[72,103,146],"VAD":[73,95,104,126,141,152,163,173],"scheme":[74,105,147,153],"evaluate":[76],"its":[77],"performance":[78],"under":[79],"eleven":[80],"types":[81,86],"noises":[83,109,182],"five":[85],"signal-to-noise":[88],"ratio":[89],"(SNR)":[90],"conditions.":[91],"Comparison":[92],"with":[93],"standard":[94],"schemes":[96],"demonstrates":[97],"accuracy":[100,164],"averaged":[106],"over":[107],"all":[108,111],"SNRs":[112],"is":[113],"~6%":[114],"(absolute)":[115],"better":[116],"than":[117],"obtained":[119,142],"by":[120,143],"best":[122,150],"among":[123],"considered":[125,151],"schemes,":[127],"namely":[128],"AMR-VAD2.":[129],"also":[131],"that,":[133],"at":[134,174],"-10":[135],"dB":[136],"SNR,":[137],"accuracies":[139],"proposed":[145],"are":[154],"88.49%":[155],"79.30%,":[157],"respectively.":[158],"This":[159],"improvement":[160],"in":[161],"indicates":[165],"robustness":[167],"low":[175],"SNR":[176],"condition":[177],"most":[179],"considered.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":17},{"year":2015,"cited_by_count":24},{"year":2014,"cited_by_count":16},{"year":2013,"cited_by_count":19},{"year":2012,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}