{"id":"https://openalex.org/W2181253919","doi":"https://doi.org/10.1186/s13634-015-0277-z","title":"Features for voice activity detection: a comparative analysis","display_name":"Features for voice activity detection: a comparative analysis","publication_year":2015,"publication_date":"2015-11-11","ids":{"openalex":"https://openalex.org/W2181253919","doi":"https://doi.org/10.1186/s13634-015-0277-z","mag":"2181253919"},"language":"en","primary_location":{"id":"doi:10.1186/s13634-015-0277-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13634-015-0277-z","pdf_url":"https://asp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13634-015-0277-z","source":{"id":"https://openalex.org/S35920007","display_name":"EURASIP Journal on Advances in Signal Processing","issn_l":"1110-8657","issn":["1110-8657","1687-0433","1687-6172","1687-6180"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Advances in Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13634-015-0277-z","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101549063","display_name":"Simon Graf","orcid":"https://orcid.org/0000-0001-9572-3997"},"institutions":[{"id":"https://openalex.org/I32021983","display_name":"Christian-Albrechts-Universit\u00e4t zu Kiel","ror":"https://ror.org/04v76ef78","country_code":"DE","type":"education","lineage":["https://openalex.org/I32021983"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Simon Graf","raw_affiliation_strings":["Acoustic Speech Enhancement Research, Nuance Communications Deutschland GmbH, S\u00f6flinger Stra\u00dfe 100, Ulm, 89077, Germany","Digital Signal Processing and System Theory, Christian-Albrechts-Universit\u00e4t zu Kiel, Kiel, 24143, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Acoustic Speech Enhancement Research, Nuance Communications Deutschland GmbH, S\u00f6flinger Stra\u00dfe 100, Ulm, 89077, Germany","institution_ids":[]},{"raw_affiliation_string":"Digital Signal Processing and System Theory, Christian-Albrechts-Universit\u00e4t zu Kiel, Kiel, 24143, Germany","institution_ids":["https://openalex.org/I32021983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090579773","display_name":"Tobias Herbig","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tobias Herbig","raw_affiliation_strings":["Acoustic Speech Enhancement Research, Nuance Communications Deutschland GmbH, S\u00f6flinger Stra\u00dfe 100, Ulm, 89077, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Acoustic Speech Enhancement Research, Nuance Communications Deutschland GmbH, S\u00f6flinger Stra\u00dfe 100, Ulm, 89077, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018562606","display_name":"Markus Buck","orcid":"https://orcid.org/0000-0002-4517-7534"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Markus Buck","raw_affiliation_strings":["Acoustic Speech Enhancement Research, Nuance Communications Deutschland GmbH, S\u00f6flinger Stra\u00dfe 100, Ulm, 89077, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Acoustic Speech Enhancement Research, Nuance Communications Deutschland GmbH, S\u00f6flinger Stra\u00dfe 100, Ulm, 89077, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036539497","display_name":"Gerhard Schmidt","orcid":"https://orcid.org/0000-0002-6128-4831"},"institutions":[{"id":"https://openalex.org/I32021983","display_name":"Christian-Albrechts-Universit\u00e4t zu Kiel","ror":"https://ror.org/04v76ef78","country_code":"DE","type":"education","lineage":["https://openalex.org/I32021983"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Schmidt","raw_affiliation_strings":["Digital Signal Processing and System Theory, Christian-Albrechts-Universit\u00e4t zu Kiel, Kiel, 24143, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Signal Processing and System Theory, Christian-Albrechts-Universit\u00e4t zu Kiel, Kiel, 24143, Germany","institution_ids":["https://openalex.org/I32021983"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101549063"],"corresponding_institution_ids":["https://openalex.org/I32021983"],"apc_list":{"value":1665,"currency":"USD","value_usd":1665},"apc_paid":{"value":1665,"currency":"USD","value_usd":1665},"fwci":5.2329,"has_fulltext":true,"cited_by_count":69,"citation_normalized_percentile":{"value":0.95719044,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"2015","issue":"1","first_page":null,"last_page":null},"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":0.9997000098228455,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8291630148887634},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.7791829109191895},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7160394191741943},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6576217412948608},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6383523941040039},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4967647194862366},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4720476567745209},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.42400598526000977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26301538944244385},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12083366513252258},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.10763147473335266}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8291630148887634},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.7791829109191895},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7160394191741943},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6576217412948608},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6383523941040039},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4967647194862366},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4720476567745209},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.42400598526000977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26301538944244385},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12083366513252258},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.10763147473335266},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1186/s13634-015-0277-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13634-015-0277-z","pdf_url":"https://asp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13634-015-0277-z","source":{"id":"https://openalex.org/S35920007","display_name":"EURASIP Journal on Advances in Signal Processing","issn_l":"1110-8657","issn":["1110-8657","1687-0433","1687-6172","1687-6180"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Advances in Signal Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1186/s13634-015-0277-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13634-015-0277-z","pdf_url":"https://asp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13634-015-0277-z","source":{"id":"https://openalex.org/S35920007","display_name":"EURASIP Journal on Advances in Signal Processing","issn_l":"1110-8657","issn":["1110-8657","1687-0433","1687-6172","1687-6180"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Advances in Signal Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6700000166893005}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321553","display_name":"Christian-Albrechts-Universit\u00e4t zu Kiel","ror":"https://ror.org/04v76ef78"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2181253919.pdf","grobid_xml":"https://content.openalex.org/works/W2181253919.grobid-xml"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W35290520","https://openalex.org/W36345725","https://openalex.org/W86846425","https://openalex.org/W120645292","https://openalex.org/W175094223","https://openalex.org/W1506438021","https://openalex.org/W1541452272","https://openalex.org/W1547828202","https://openalex.org/W1585607783","https://openalex.org/W1585785493","https://openalex.org/W1586113758","https://openalex.org/W1635512741","https://openalex.org/W1829004877","https://openalex.org/W1965559434","https://openalex.org/W1974387177","https://openalex.org/W1990934990","https://openalex.org/W1997810056","https://openalex.org/W2007119422","https://openalex.org/W2009010671","https://openalex.org/W2009568299","https://openalex.org/W2013312573","https://openalex.org/W2023582935","https://openalex.org/W2032474878","https://openalex.org/W2051428568","https://openalex.org/W2056116740","https://openalex.org/W2073693905","https://openalex.org/W2083569984","https://openalex.org/W2097036989","https://openalex.org/W2098265087","https://openalex.org/W2098471762","https://openalex.org/W2099105119","https://openalex.org/W2100502431","https://openalex.org/W2108289863","https://openalex.org/W2108819501","https://openalex.org/W2115717467","https://openalex.org/W2121973264","https://openalex.org/W2123550723","https://openalex.org/W2126693545","https://openalex.org/W2128838222","https://openalex.org/W2129120544","https://openalex.org/W2130426352","https://openalex.org/W2131833400","https://openalex.org/W2135780429","https://openalex.org/W2144256180","https://openalex.org/W2149759367","https://openalex.org/W2152960771","https://openalex.org/W2156038773","https://openalex.org/W2159105055","https://openalex.org/W2159856503","https://openalex.org/W2170644918","https://openalex.org/W2181395726","https://openalex.org/W2201660484","https://openalex.org/W2294745040","https://openalex.org/W2294819182","https://openalex.org/W2394998899","https://openalex.org/W2401827384","https://openalex.org/W2407232066","https://openalex.org/W3007258144","https://openalex.org/W3127686677","https://openalex.org/W3145636786","https://openalex.org/W3147539069","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2069501481","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W2103239478","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340"],"abstract_inverted_index":{"In":[0,56],"many":[1],"speech":[2,24,30,40],"signal":[3],"processing":[4],"applications,":[5],"voice":[6],"activity":[7,25],"detection":[8],"(VAD)":[9],"plays":[10],"an":[11,16],"essential":[12],"role":[13],"for":[14,121],"separating":[15],"audio":[17],"stream":[18],"into":[19],"time":[20,27],"intervals":[21,28],"that":[22,35,70,85],"contain":[23],"and":[26,94,126,133],"where":[29],"is":[31,107],"absent.":[32],"Many":[33],"features":[34,69,80,125],"reflect":[36],"the":[37,79,96],"presence":[38],"of":[39,65,75,98,104],"were":[41],"introduced":[42],"in":[43,109],"literature.":[44],"However,":[45],"to":[46,83,111],"our":[47],"knowledge,":[48],"no":[49],"extensive":[50],"comparison":[51],"has":[52],"been":[53],"provided":[54],"yet.":[55],"this":[57],"article,":[58],"we":[59],"therefore":[60],"present":[61],"a":[62,128],"structured":[63],"overview":[64],"several":[66],"established":[67],"VAD":[68,124],"target":[71],"at":[72],"different":[73,116],"properties":[74,84],"speech.":[76],"We":[77],"categorize":[78],"with":[81],"respect":[82],"are":[86],"exploited,":[87],"such":[88],"as":[89],"power,":[90],"harmonicity,":[91],"or":[92],"modulation,":[93],"evaluate":[95],"performance":[97,132],"some":[99],"dedicated":[100],"features.":[101],"The":[102],"importance":[103],"temporal":[105],"context":[106],"discussed":[108],"relation":[110],"latency":[112],"restrictions":[113],"imposed":[114],"by":[115],"applications.":[117],"Our":[118],"analyses":[119],"allow":[120],"selecting":[122],"promising":[123],"finding":[127],"reasonable":[129],"trade-off":[130],"between":[131],"complexity.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":7}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
