{"id":"https://openalex.org/W2240641835","doi":"https://doi.org/10.1109/lsp.2015.2495219","title":"Voice Activity Detection: Merging Source and Filter-based Information","display_name":"Voice Activity Detection: Merging Source and Filter-based Information","publication_year":2015,"publication_date":"2015-10-27","ids":{"openalex":"https://openalex.org/W2240641835","doi":"https://doi.org/10.1109/lsp.2015.2495219","mag":"2240641835"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2015.2495219","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1903.02844","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029023520","display_name":"Thomas Drugman","orcid":"https://orcid.org/0000-0002-1491-7878"},"institutions":[{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Drugman","raw_affiliation_strings":["Toshiba Cambridge Research Laboratory, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Toshiba Cambridge Research Laboratory, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035745788","display_name":"Yannis Stylianou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yannis Stylianou","raw_affiliation_strings":["Toshiba Cambridge Research Laboratory, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Toshiba Cambridge Research Laboratory, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109488356","display_name":"Yusuke Kida","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yusuke Kida","raw_affiliation_strings":["Toshiba Cambridge Research Laboratory, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Toshiba Cambridge Research Laboratory, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112250968","display_name":"Masami Akamine","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Masami Akamine","raw_affiliation_strings":["Toshiba Cambridge Research Laboratory, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Toshiba Cambridge Research Laboratory, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.106,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":72,"citation_normalized_percentile":{"value":0.941014,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"23","issue":"2","first_page":"252","last_page":"256"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech Enhancement Techniques","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 Enhancement Techniques","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 Technology","score":0.9996,"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":"Audio Signal Classification and Analysis","score":0.9994,"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/audio-event-detection","display_name":"Audio Event Detection","score":0.597507},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker Verification","score":0.590096},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.58610255},{"id":"https://openalex.org/keywords/environmental-sound-recognition","display_name":"Environmental Sound Recognition","score":0.570958},{"id":"https://openalex.org/keywords/audio-visual-speech-recognition","display_name":"Audio-Visual Speech Recognition","score":0.570507},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source Separation","score":0.56997},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.45917654},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.45749176},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.42759955}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.790449},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.58610255},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5571915},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5529834},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.550061},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.5145518},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4826196},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.46605736},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4593056},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.45917654},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.45749176},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44106025},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.42759955},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.42038465},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.41055387},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41027927},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.13743088},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2015.2495219","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1903.02844","pdf_url":"https://arxiv.org/pdf/1903.02844","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://api.datacite.org/dois/10.48550/arxiv.1903.02844","pdf_url":null,"source":{"id":"https://openalex.org/S4393179698","display_name":"DataCite API","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210145204","host_organization_name":"DataCite","host_organization_lineage":["https://openalex.org/I4210145204"],"host_organization_lineage_names":["DataCite"],"type":"metadata"},"license":null,"license_id":null,"version":null}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1903.02844","pdf_url":"https://arxiv.org/pdf/1903.02844","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"score":0.47,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions"},{"score":0.46,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"grants":[],"datasets":[],"versions":["https://openalex.org/W2240641835","https://openalex.org/W3101370029"],"referenced_works_count":44,"referenced_works":["https://openalex.org/W175094223","https://openalex.org/W1965559434","https://openalex.org/W1975748432","https://openalex.org/W1981341575","https://openalex.org/W1999319498","https://openalex.org/W1999454387","https://openalex.org/W2023582935","https://openalex.org/W2023684629","https://openalex.org/W2029147192","https://openalex.org/W2052043304","https://openalex.org/W2052384514","https://openalex.org/W2073693905","https://openalex.org/W2090861223","https://openalex.org/W2095176743","https://openalex.org/W2098265087","https://openalex.org/W2099076569","https://openalex.org/W2115717467","https://openalex.org/W2117468249","https://openalex.org/W2126693545","https://openalex.org/W2129120544","https://openalex.org/W2130814876","https://openalex.org/W2132214951","https://openalex.org/W2142170306","https://openalex.org/W2149053750","https://openalex.org/W2153754015","https://openalex.org/W2154278880","https://openalex.org/W2156038773","https://openalex.org/W2156798212","https://openalex.org/W2158275940","https://openalex.org/W2158353947","https://openalex.org/W2165034386","https://openalex.org/W2170644918","https://openalex.org/W2294819182","https://openalex.org/W2397375888","https://openalex.org/W2397741330","https://openalex.org/W2402212287","https://openalex.org/W2403186097","https://openalex.org/W3015571647","https://openalex.org/W304112886","https://openalex.org/W3127686677","https://openalex.org/W3145636786","https://openalex.org/W36345725","https://openalex.org/W4237171445","https://openalex.org/W86289693"],"related_works":["https://openalex.org/W842936808","https://openalex.org/W4234886518","https://openalex.org/W3174028392","https://openalex.org/W2509844848","https://openalex.org/W2486541857","https://openalex.org/W2466816617","https://openalex.org/W2389591058","https://openalex.org/W2382112581","https://openalex.org/W1970834875","https://openalex.org/W1969920786"],"abstract_inverted_index":{"Voice":[0],"Activity":[1],"Detection":[2],"(VAD)":[3],"refers":[4],"to":[5,47,95,128,142],"the":[6,30,36,39,49,67,71,78,114,143,157,162],"problem":[7],"of":[8,38,43,52,80,111,113,135,145,169],"distinguishing":[9],"speech":[10],"segments":[11],"from":[12,29],"background":[13],"noise.":[14],"Numerous":[15],"approaches":[16],"have":[17],"been":[18],"proposed":[19,72,94,124,158],"for":[20,66],"this":[21,44],"purpose.":[22],"Some":[23],"are":[24,76,93],"based":[25],"on":[26,87,132,176],"features":[27,75],"derived":[28],"power":[31,65],"spectral":[32],"density,":[33],"others":[34],"exploit":[35],"periodicity":[37],"signal.":[40],"The":[41,74,122],"goal":[42],"paper":[45],"is":[46,126],"investigate":[48],"joint":[50],"use":[51],"source":[53,97],"and":[54,98,102,152],"filter-based":[55],"features.":[56],"Interestingly,":[57],"a":[58,88,166],"mutual":[59],"information-based":[60],"assessment":[61],"shows":[62],"superior":[63],"discrimination":[64],"source-related":[68,147],"features,":[69,148],"especially":[70],"ones.":[73],"further":[77],"input":[79],"an":[81,108],"artificial":[82],"neural":[83],"network-based":[84],"classifier":[85],"trained":[86],"multi-condition":[89,150],"database.":[90],"Two":[91],"strategies":[92],"merge":[96],"filter":[99],"information:":[100],"feature":[101],"decision":[103,120],"fusion.":[104,121],"Our":[105],"experiments":[106],"indicate":[107],"absolute":[109,175],"reduction":[110],"3%":[112],"equal":[115],"error":[116],"rate":[117],"when":[118],"using":[119],"final":[123],"system":[125,159],"compared":[127],"four":[129],"state-of-the-art":[130,164],"methods":[131],"150":[133],"minutes":[134],"data":[136],"recorded":[137],"in":[138],"real":[139],"environments.":[140],"Thanks":[141],"robustness":[144],"its":[146,149,153],"training":[151],"efficient":[154],"information":[155],"fusion,":[156],"yields":[160],"over":[161],"best":[163],"VAD":[165],"substantial":[167],"increase":[168],"accuracy":[170],"across":[171],"all":[172],"conditions":[173],"(24%":[174],"average).":[177]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2240641835","counts_by_year":[{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":3}],"updated_date":"2024-11-30T09:07:55.615375","created_date":"2016-06-24"}