{"id":"https://openalex.org/W70858058","doi":"https://doi.org/10.21437/interspeech.2004-347","title":"Improved voice activity detection combining noise reduction and subband divergence measures","display_name":"Improved voice activity detection combining noise reduction and subband divergence measures","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W70858058","doi":"https://doi.org/10.21437/interspeech.2004-347","mag":"70858058"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-347","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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":"Jos\u00e9 Carlos 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":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Antonio Rubio","raw_affiliation_strings":["[University of Granada]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[University of Granada]","institution_ids":["https://openalex.org/I173304897"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"961","last_page":"964"},"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":0.9995999932289124,"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/divergence","display_name":"Divergence (linguistics)","score":0.7494074106216431},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7353102564811707},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7214463949203491},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6677848100662231},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6341460347175598},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5788727402687073},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5244565010070801},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.48571261763572693},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4700091481208801},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4692278802394867},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.45000576972961426},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.41998594999313354},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.38449499011039734},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3288518190383911},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12621676921844482},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09961351752281189},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.09335383772850037}],"concepts":[{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.7494074106216431},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7353102564811707},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7214463949203491},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6677848100662231},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6341460347175598},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5788727402687073},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5244565010070801},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.48571261763572693},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4700091481208801},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4692278802394867},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.45000576972961426},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.41998594999313354},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.38449499011039734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3288518190383911},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12621676921844482},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09961351752281189},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.09335383772850037},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2004-347","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.75.5097","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.75.5097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://sirio.ugr.es/segura/pdfdocs/ICSLP2004a.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1897045322","https://openalex.org/W1979012094","https://openalex.org/W2032362923","https://openalex.org/W2099105119","https://openalex.org/W2099145922","https://openalex.org/W2117321034","https://openalex.org/W2120353785","https://openalex.org/W2129120544","https://openalex.org/W2135445137","https://openalex.org/W2156038773","https://openalex.org/W2156472550","https://openalex.org/W2163634074","https://openalex.org/W2407641997"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W3108403339","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W2162712524","https://openalex.org/W4287867034","https://openalex.org/W2175872006","https://openalex.org/W2052688117","https://openalex.org/W3005783148"],"abstract_inverted_index":{"Currently,":[0],"new":[1],"trends":[2],"in":[3,11,25,71],"wireless":[4],"communications":[5],"are":[6,16,120],"demanding":[7],"reliable":[8],"human-machine":[9],"interaction":[10],"real-life":[12],"environments.":[13,27,73],"However,":[14],"there":[15],"obstacles":[17],"inhibiting":[18],"automatic":[19],"speech":[20,68,90,138],"recognition":[21,139],"systems":[22,37],"(ASR)":[23],"working":[24],"noisy":[26,72],"The":[28,74],"main":[29],"difficulty":[30],"is":[31],"the":[32,65,77,82,85,94,99,129,132],"degradation":[33],"suffered":[34],"by":[35,80],"ASR":[36],"due":[38],"to":[39],"a":[40,104,123],"mismatch":[41],"between":[42,84],"training":[43],"and":[44,59,91,117,128],"test":[45],"conditions.":[46],"This":[47],"paper":[48],"shows":[49],"an":[50],"improved":[51],"voice":[52],"activity":[53],"detector":[54],"(VAD)":[55],"combining":[56],"noise":[57,92],"reduction":[58],"subband":[60,86],"divergence":[61,83],"estimation":[62],"for":[63,136],"improving":[64],"reliability":[66],"of":[67,89,131],"recognizers":[69],"operating":[70],"algorithm":[75],"formulates":[76],"decision":[78],"rule":[79],"measuring":[81],"spectral":[87],"magnitude":[88],"using":[93],"Kullback-Leibler":[95],"(KL)":[96],"distance":[97],"on":[98],"denoised":[100],"signal.":[101],"Experiments":[102],"demonstrate":[103],"sustained":[105],"advantage":[106],"over":[107],"different":[108],"VAD":[109],"methods":[110],"including":[111],"standard":[112],"VADs":[113,130],"such":[114],"as":[115,122],"G.729":[116],"AMR,":[118],"which":[119],"used":[121],"reference,":[124],"recently":[125],"reported":[126],"algorithms,":[127],"advanced":[133],"frontend":[134],"(AFE)":[135],"distributed":[137],"(DSR).":[140],"1.":[141]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
