{"id":"https://openalex.org/W109290487","doi":"https://doi.org/10.21437/interspeech.2007-730","title":"Environmentally aware voice activity detector","display_name":"Environmentally aware voice activity detector","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W109290487","doi":"https://doi.org/10.21437/interspeech.2007-730","mag":"109290487"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-730","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-730","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","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/A5111469714","display_name":"Abhijeet Sangwan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abhijeet Sangwan","raw_affiliation_strings":["University of Texas at Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083556118","display_name":"Nitish Krishnamurthy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nitish Krishnamurthy","raw_affiliation_strings":["University of Texas at Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John H. L. Hansen","raw_affiliation_strings":["Electrical Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3255,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.54121123,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2929","last_page":"2932"},"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":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":0.9994999766349792,"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/noise","display_name":"Noise (video)","score":0.7602515816688538},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7155944108963013},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.677229106426239},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6697186827659607},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6637819409370422},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5583479404449463},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5087645649909973},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.5006933212280273},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.45364025235176086},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4426339268684387},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4394943118095398},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.43563374876976013},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34731465578079224},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3353903889656067},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.23889991641044617},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.15508845448493958},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.15159237384796143}],"concepts":[{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.7602515816688538},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7155944108963013},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.677229106426239},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6697186827659607},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6637819409370422},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5583479404449463},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5087645649909973},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.5006933212280273},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.45364025235176086},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4426339268684387},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4394943118095398},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.43563374876976013},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34731465578079224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3353903889656067},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.23889991641044617},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.15508845448493958},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.15159237384796143},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2007-730","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-730","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W44176993","https://openalex.org/W57135315","https://openalex.org/W1966976522","https://openalex.org/W1994552544","https://openalex.org/W2094709280","https://openalex.org/W2114294947","https://openalex.org/W2121973264","https://openalex.org/W2139212933","https://openalex.org/W2170389424","https://openalex.org/W2485688913"],"related_works":["https://openalex.org/W2418631473","https://openalex.org/W2364132456","https://openalex.org/W2390182490","https://openalex.org/W2183143893","https://openalex.org/W2357471906","https://openalex.org/W4200341926","https://openalex.org/W4206754781","https://openalex.org/W2075390205","https://openalex.org/W4211118001","https://openalex.org/W2071001100"],"abstract_inverted_index":{"Abstract":[0],"Traditional":[1],"voice":[2,182],"activity":[3,183],"detectors":[4],"(VADs)":[5],"tend":[6],"to":[7,10,31,115],"be":[8],"deaf":[9],"theacoustical":[11],"background":[12,34,97],"noise,":[13],"as":[14],"they":[15],"(i)":[16],"utilize":[17],"a":[18,146],"single":[19],"operatingpoint":[20],"for":[21,176],"all":[22],"SNRs":[23],"(signal-to-noise":[24],"ratios)":[25],"and":[26,67,103,110,121,158],"noise":[27,35,83,92,101,108,180],"types,":[28],"and(ii)":[29],"attempt":[30],"learn":[32],"the":[33,47,70,87,95,100,107,117,124,131,135,156],"model":[36],"online":[37],"from":[38,155],"\ufb01-nite":[39],"data":[40,152],"length.":[41],"In":[42,85],"this":[43,113],"paper,":[44],"we":[45],"address":[46],"aforementionedissues":[48],"by":[49,98],"designing":[50],"an":[51,162],"environmentally":[52],"aware":[53],"(EA)":[54],"VAD.":[55,126],"TheEA":[56],"VAD":[57,76,89],"scheme":[58],"builds":[59],"prior":[60],"of\ufb02ine":[61],"knowledge":[62],"of":[63,94,106,130,165],"commonlyencountered":[64],"acoustical":[65],"backgrounds,":[66],"also":[68],"combines":[69],"re-cently":[71],"proposed":[72],"competitive":[73],"Neyman-Pearson":[74],"(CNP)":[75],"witha":[77],"SVM":[78],"(support":[79],"vector":[80],"machine)":[81],"based":[82],"classi\ufb01er.":[84],"oper-ation,":[86],"EA":[88,132],"obtains":[90],"accurate":[91],"models":[93],"acous-tical":[96],"employing":[99],"classi\ufb01er":[102],"its":[104],"priorknowledge":[105],"type,":[109],"thereafter":[111],"uses":[112],"informa-tion":[114],"set":[116],"best":[118],"operating":[119],"point":[120],"initialization":[122],"parametersfor":[123],"CNP":[125],"The":[127],"superior":[128],"performance":[129],"VADscheme":[133],"over":[134,170],"standard":[136],"AMR":[137,171],"(adaptive":[138],"multi-rate)":[139],"VADs":[140,172],"inlow":[141],"SNR":[142,175],"is":[143],"con\ufb01rmed":[144],"in":[145,167,173],"simulation":[147],"study,":[148],"where":[149],"speech":[150],"andnoise":[151],"were":[153],"drawn":[154],"SWITCHBOARD":[157],"NOISEXdatabases.":[159],"We":[160],"report":[161],"absolute":[163],"improvement":[164],"10-15%":[166],"de-tection":[168],"rates":[169],"low":[174],"different":[177],"noisetypes.Index":[178],"Terms:":[179],"modeling,":[181],"detector,":[184],"environ-mental":[185],"snif\ufb01ng":[186]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}