{"id":"https://openalex.org/W38512374","doi":"https://doi.org/10.21437/eurospeech.2003-535","title":"A new adaptive long-term spectral estimation voice activity detector","display_name":"A new adaptive long-term spectral estimation voice activity detector","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W38512374","doi":"https://doi.org/10.21437/eurospeech.2003-535","mag":"38512374"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-535","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","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/A5067023995","display_name":"Javier Ram\u0131\u0301rez","orcid":"https://orcid.org/0000-0002-6229-2921"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Javier Ramirez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000645757","display_name":"Jos\u00e9 C. Segura","orcid":"https://orcid.org/0000-0003-3746-0978"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jose C. Segura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032065113","display_name":"Carmen Ben\u0131\u0301tez","orcid":"https://orcid.org/0000-0002-5407-8335"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carmen Benitez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014325055","display_name":"\u00c1ngel de la Torre","orcid":"https://orcid.org/0000-0002-9736-5190"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Angel de la Torre","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103257592","display_name":"Antonio J. Rubio","orcid":"https://orcid.org/0000-0003-3814-0335"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antonio J. Rubio","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3041","last_page":"3044"},"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":0.9994999766349792,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/speech-recognition","display_name":"Speech recognition","score":0.7804791927337646},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7634519338607788},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.7024573087692261},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.6993045210838318},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.6305615901947021},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6005162596702576},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.5148190855979919},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.505779504776001},{"id":"https://openalex.org/keywords/sliding-window-protocol","display_name":"Sliding window protocol","score":0.49986791610717773},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.46067342162132263},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.45655953884124756},{"id":"https://openalex.org/keywords/envelope","display_name":"Envelope (radar)","score":0.44261205196380615},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4373202919960022},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4126986563205719},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4108668565750122},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26927363872528076},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.2662850022315979},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.18377166986465454},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12085211277008057},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11116749048233032},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07473674416542053}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7804791927337646},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7634519338607788},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.7024573087692261},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.6993045210838318},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.6305615901947021},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6005162596702576},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5148190855979919},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.505779504776001},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.49986791610717773},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.46067342162132263},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.45655953884124756},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.44261205196380615},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4373202919960022},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4126986563205719},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4108668565750122},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26927363872528076},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.2662850022315979},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.18377166986465454},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12085211277008057},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11116749048233032},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07473674416542053},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.2003-535","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W181306761","https://openalex.org/W202024829","https://openalex.org/W1897045322","https://openalex.org/W1985456342","https://openalex.org/W2099145922","https://openalex.org/W2117321034","https://openalex.org/W2120353785","https://openalex.org/W2128653836","https://openalex.org/W2129120544","https://openalex.org/W2135445137","https://openalex.org/W2149535104","https://openalex.org/W2151484683","https://openalex.org/W2156038773","https://openalex.org/W2407641997"],"related_works":["https://openalex.org/W2294333436","https://openalex.org/W2653598178","https://openalex.org/W2747006289","https://openalex.org/W2072884270","https://openalex.org/W4252682934","https://openalex.org/W2135485548","https://openalex.org/W2052787172","https://openalex.org/W2002243964","https://openalex.org/W4375869276","https://openalex.org/W1585241115"],"abstract_inverted_index":{"This":[0],"paper":[1],"shows":[2],"an":[3],"efficient":[4],"voice":[5],"activity":[6],"detector":[7],"(VAD)":[8],"that":[9],"is":[10,80,91,101,110,124],"based":[11],"on":[12],"the":[13,16,31,44,51,63,77,83,96,107,114,127,134],"estimation":[14],"of":[15,66,106,138],"long-term":[17,45],"spectral":[18],"diver-":[19],"gence":[20],"(LTSD)":[21],"between":[22],"noise":[23,85],"and":[24,49,61,117,141,153],"speech":[25,36,74],"periods.":[26],"The":[27,121],"proposed":[28,108,122],"method":[29],"decomposes":[30],"input":[32],"signal":[33],"into":[34],"overlapped":[35],"frames,":[37],"uses":[38],"a":[39,56,88,147],"sliding":[40],"window":[41],"to":[42,71,82,126],"compute":[43],"spec-":[46],"tral":[47],"envelope":[48],"measures":[50],"speech/non-speech":[52,139],"LTSD,":[53],"thus":[54],"yielding":[55],"high":[57],"discriminating":[58],"decision":[59,67,78],"rule":[60],"minimizing":[62],"average":[64],"number":[65],"errors.":[68],"In":[69],"order":[70],"increase":[72],"non-":[73],"detection":[75,140],"accuracy,":[76],"threshold":[79],"adapted":[81],"measured":[84],"energy":[86],"while":[87],"controlled":[89],"hang-over":[90],"ac-":[92],"tivated":[93],"only":[94],"when":[95],"observed":[97],"signal-to-noise":[98],"ratio":[99],"(SNR)":[100],"low.":[102],"An":[103],"exhaustive":[104],"analysis":[105],"VAD":[109,123],"carried":[111],"out":[112],"using":[113],"AURORA":[115],"TIdigits":[116],"SpeechDat-Car":[118],"(SDC)":[119],"databases.":[120],"compared":[125],"most":[128],"com-":[129],"monly":[130],"used":[131],"ones":[132],"in":[133,136],"field":[135],"terms":[137],"recognition":[142],"performance.":[143],"Experimental":[144],"results":[145],"demonstrate":[146],"sustained":[148],"advantage":[149],"over":[150],"G.729,":[151],"AMR":[152],"AFE":[154],"VADs.":[155]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}