{"id":"https:\/\/openalex.org\/W2108913645","doi":"https:\/\/doi.org\/10.1109\/icassp.2004.1326056","title":"A differential spectral voice activity detector","display_name":"A differential spectral voice activity detector","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https:\/\/openalex.org\/W2108913645","doi":"https:\/\/doi.org\/10.1109\/icassp.2004.1326056","mag":"2108913645"},"language":"en","primary_location":{"id":"doi:10.1109\/icassp.2004.1326056","is_oa":false,"landing_page_url":"https:\/\/doi.org\/10.1109\/icassp.2004.1326056","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","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\/A5081808619","display_name":"Philip N. Garner","orcid":"https:\/\/orcid.org\/0000-0002-0814-1348"},"institutions":[{"id":"https:\/\/openalex.org\/I1320697193","display_name":"Canon (Japan)","ror":"https:\/\/ror.org\/05gg0gh87","country_code":"JP","type":"company","lineage":["https:\/\/openalex.org\/I1320697193"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"P.N. Garner","raw_affiliation_strings":["Canon, Inc., Ota, Tokyo, Japan","Canon INC., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Canon, Inc., Ota, Tokyo, Japan","institution_ids":["https:\/\/openalex.org\/I1320697193"]},{"raw_affiliation_string":"Canon INC., Tokyo, Japan","institution_ids":["https:\/\/openalex.org\/I1320697193"]}]},{"author_position":"middle","author":{"id":"https:\/\/openalex.org\/A5041393610","display_name":"Toshiaki Fukada","orcid":null},"institutions":[{"id":"https:\/\/openalex.org\/I1320697193","display_name":"Canon (Japan)","ror":"https:\/\/ror.org\/05gg0gh87","country_code":"JP","type":"company","lineage":["https:\/\/openalex.org\/I1320697193"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T. Fukada","raw_affiliation_strings":["Canon, Inc., Ota, Tokyo, Japan","Canon INC., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Canon, Inc., Ota, Tokyo, Japan","institution_ids":["https:\/\/openalex.org\/I1320697193"]},{"raw_affiliation_string":"Canon INC., Tokyo, Japan","institution_ids":["https:\/\/openalex.org\/I1320697193"]}]},{"author_position":"last","author":{"id":"https:\/\/openalex.org\/A5048447624","display_name":"Yasuhiro Komori","orcid":"https:\/\/orcid.org\/0000-0003-1962-7068"},"institutions":[{"id":"https:\/\/openalex.org\/I1320697193","display_name":"Canon (Japan)","ror":"https:\/\/ror.org\/05gg0gh87","country_code":"JP","type":"company","lineage":["https:\/\/openalex.org\/I1320697193"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Y. Komori","raw_affiliation_strings":["Canon, Inc., Ota, Tokyo, Japan","Canon INC., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Canon, Inc., Ota, Tokyo, Japan","institution_ids":["https:\/\/openalex.org\/I1320697193"]},{"raw_affiliation_string":"Canon INC., Tokyo, Japan","institution_ids":["https:\/\/openalex.org\/I1320697193"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https:\/\/openalex.org\/I1320697193"],"apc_list":null,"apc_paid":null,"fwci":0.5178,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.5828845,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"597"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https:\/\/openalex.org\/T10860","display_name":"Speech and Audio Processing","score":1,"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,"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":0.9994000196456909,"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":0.9994000196456909,"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\/gaussian","display_name":"Gaussian","score":0.6579407453536987},{"id":"https:\/\/openalex.org\/keywords\/detector","display_name":"Detector","score":0.6334567666053772},{"id":"https:\/\/openalex.org\/keywords\/gaussian-noise","display_name":"Gaussian noise","score":0.6179956793785095},{"id":"https:\/\/openalex.org\/keywords\/differential","display_name":"Differential (mechanical device)","score":0.6065039038658142},{"id":"https:\/\/openalex.org\/keywords\/speech-recognition","display_name":"Speech recognition","score":0.5956131219863892},{"id":"https:\/\/openalex.org\/keywords\/computer-science","display_name":"Computer science","score":0.5488907694816589},{"id":"https:\/\/openalex.org\/keywords\/noise","display_name":"Noise (video)","score":0.5484290719032288},{"id":"https:\/\/openalex.org\/keywords\/voice-activity-detection","display_name":"Voice activity detection","score":0.5271615386009216},{"id":"https:\/\/openalex.org\/keywords\/representation","display_name":"Representation (politics)","score":0.4577059745788574},{"id":"https:\/\/openalex.org\/keywords\/gaussian-network-model","display_name":"Gaussian network model","score":0.43304887413978577},{"id":"https:\/\/openalex.org\/keywords\/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36774134635925293},{"id":"https:\/\/openalex.org\/keywords\/mathematics","display_name":"Mathematics","score":0.3346521258354187},{"id":"https:\/\/openalex.org\/keywords\/artificial-intelligence","display_name":"Artificial intelligence","score":0.312138170003891},{"id":"https:\/\/openalex.org\/keywords\/speech-processing","display_name":"Speech processing","score":0.31208986043930054},{"id":"https:\/\/openalex.org\/keywords\/physics","display_name":"Physics","score":0.17939209938049316},{"id":"https:\/\/openalex.org\/keywords\/telecommunications","display_name":"Telecommunications","score":0.09828922152519226}],"concepts":[{"id":"https:\/\/openalex.org\/C163716315","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q901177","display_name":"Gaussian","level":2,"score":0.6579407453536987},{"id":"https:\/\/openalex.org\/C94915269","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q1834857","display_name":"Detector","level":2,"score":0.6334567666053772},{"id":"https:\/\/openalex.org\/C4199805","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q2725903","display_name":"Gaussian noise","level":2,"score":0.6179956793785095},{"id":"https:\/\/openalex.org\/C93226319","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.6065039038658142},{"id":"https:\/\/openalex.org\/C28490314","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q189436","display_name":"Speech recognition","level":1,"score":0.5956131219863892},{"id":"https:\/\/openalex.org\/C41008148","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q21198","display_name":"Computer science","level":0,"score":0.5488907694816589},{"id":"https:\/\/openalex.org\/C99498987","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q2210247","display_name":"Noise (video)","level":3,"score":0.5484290719032288},{"id":"https:\/\/openalex.org\/C204201278","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5271615386009216},{"id":"https:\/\/openalex.org\/C2776359362","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4577059745788574},{"id":"https:\/\/openalex.org\/C166550679","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q263400","display_name":"Gaussian network model","level":3,"score":0.43304887413978577},{"id":"https:\/\/openalex.org\/C153180895","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36774134635925293},{"id":"https:\/\/openalex.org\/C33923547","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q395","display_name":"Mathematics","level":0,"score":0.3346521258354187},{"id":"https:\/\/openalex.org\/C154945302","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q11660","display_name":"Artificial intelligence","level":1,"score":0.312138170003891},{"id":"https:\/\/openalex.org\/C61328038","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q3358061","display_name":"Speech processing","level":2,"score":0.31208986043930054},{"id":"https:\/\/openalex.org\/C121332964","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q413","display_name":"Physics","level":0,"score":0.17939209938049316},{"id":"https:\/\/openalex.org\/C76155785","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q418","display_name":"Telecommunications","level":1,"score":0.09828922152519226},{"id":"https:\/\/openalex.org\/C199539241","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q7748","display_name":"Law","level":1,"score":0},{"id":"https:\/\/openalex.org\/C94625758","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q7163","display_name":"Politics","level":2,"score":0},{"id":"https:\/\/openalex.org\/C17744445","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q36442","display_name":"Political science","level":0,"score":0},{"id":"https:\/\/openalex.org\/C115961682","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q860623","display_name":"Image (mathematics)","level":2,"score":0},{"id":"https:\/\/openalex.org\/C97355855","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q11473","display_name":"Thermodynamics","level":1,"score":0},{"id":"https:\/\/openalex.org\/C62520636","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q944","display_name":"Quantum mechanics","level":1,"score":0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109\/icassp.2004.1326056","is_oa":false,"landing_page_url":"https:\/\/doi.org\/10.1109\/icassp.2004.1326056","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.852.8031","is_oa":false,"landing_page_url":"http:\/\/citeseerx.ist.psu.edu\/viewdoc\/summary?doi=10.1.1.852.8031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http:\/\/www.idiap.ch\/%7Epgarner\/pubs\/garner2004.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https:\/\/metadata.un.org\/sdg\/16","display_name":"Peace, Justice and strong institutions","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https:\/\/openalex.org\/W6222964","https:\/\/openalex.org\/W1905857425","https:\/\/openalex.org\/W2112994876","https:\/\/openalex.org\/W2121973264","https:\/\/openalex.org\/W2129120544","https:\/\/openalex.org\/W2156038773","https:\/\/openalex.org\/W2157821739","https:\/\/openalex.org\/W2165630397","https:\/\/openalex.org\/W3147539069","https:\/\/openalex.org\/W6639950011","https:\/\/openalex.org\/W6683989643"],"related_works":["https:\/\/openalex.org\/W642007152","https:\/\/openalex.org\/W2401827384","https:\/\/openalex.org\/W2355290951","https:\/\/openalex.org\/W2069501481","https:\/\/openalex.org\/W2103239478","https:\/\/openalex.org\/W2552102772","https:\/\/openalex.org\/W1510046822","https:\/\/openalex.org\/W2052688117","https:\/\/openalex.org\/W4294771049","https:\/\/openalex.org\/W1523214805"],"abstract_inverted_index":{"The":[0,67],"voice":[1],"activity":[2],"detection":[3],"(VAD)":[4],"problem":[5],"is":[6,24,34,64,71],"placed":[7],"into":[8],"a":[9,57,62,85],"decision":[10],"theoretic":[11],"framework,":[12],"and":[13,47,53],"the":[14,31,37,80],"Gaussian":[15,38,82],"VAD":[16,70,83],"model":[17,39,63],"of":[18,51],"Sohn":[19],"et":[20],"al.":[21],"(1998,":[22],"1999)":[23],"then":[25,72],"shown":[26,73],"to":[27,45,76],"fit":[28],"well":[29],"with":[30,79],"framework.":[32],"It":[33],"argued":[35],"that":[36],"can":[40],"be":[41],"made":[42],"more":[43],"robust":[44],"correlation":[46],"expected":[48],"spectral":[49,59,69],"shapes":[50],"speech":[52,86],"noise":[54],"by":[55,74],"using":[56],"differential":[58,68],"representation.":[60],"Such":[61],"formulated":[65],"theoretically.":[66],"experiment":[75],"compare":[77],"favourably":[78],"basic":[81],"in":[84],"recognition":[87],"setting,":[88],"especially":[89],"for":[90],"noisy":[91],"environments.":[92]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}