{"id":"https://openalex.org/W4387542675","doi":"https://doi.org/10.1109/roedunet60162.2023.10274921","title":"Improved Speech Activity Detection Model Using Convolutional Neural Networks","display_name":"Improved Speech Activity Detection Model Using Convolutional Neural Networks","publication_year":2023,"publication_date":"2023-09-21","ids":{"openalex":"https://openalex.org/W4387542675","doi":"https://doi.org/10.1109/roedunet60162.2023.10274921"},"language":"en","primary_location":{"id":"doi:10.1109/roedunet60162.2023.10274921","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/roedunet60162.2023.10274921","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 22nd RoEduNet Conference: Networking in Education and Research (RoEduNet)","raw_type":"proceedings-article"},"type":"article","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/A5093045467","display_name":"Costin-Alexandru Deonise","orcid":null},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Costin-Alexandru Deonise","raw_affiliation_strings":["National University of Science and Technology Politehnica,Bucharest,Romania","National University of Science and Technology Politehnica, Bucharest, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Science and Technology Politehnica,Bucharest,Romania","institution_ids":["https://openalex.org/I61641377"]},{"raw_affiliation_string":"National University of Science and Technology Politehnica, Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093045468","display_name":"Taisia-Maria Coconu","orcid":null},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Taisia-Maria Coconu","raw_affiliation_strings":["National University of Science and Technology Politehnica,Bucharest,Romania","National University of Science and Technology Politehnica, Bucharest, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Science and Technology Politehnica,Bucharest,Romania","institution_ids":["https://openalex.org/I61641377"]},{"raw_affiliation_string":"National University of Science and Technology Politehnica, Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077365712","display_name":"Traian Rebedea","orcid":"https://orcid.org/0000-0002-7255-5537"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Traian Rebedea","raw_affiliation_strings":["National University of Science and Technology Politehnica,Bucharest,Romania","National University of Science and Technology Politehnica, Bucharest, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Science and Technology Politehnica,Bucharest,Romania","institution_ids":["https://openalex.org/I61641377"]},{"raw_affiliation_string":"National University of Science and Technology Politehnica, Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027328407","display_name":"Florin Pop","orcid":"https://orcid.org/0000-0002-4566-1545"},"institutions":[{"id":"https://openalex.org/I33800924","display_name":"Academia Oamenilor de \u0218tiin\u021b\u0103 din Rom\u00e2nia","ror":"https://ror.org/04ybnj478","country_code":"RO","type":"facility","lineage":["https://openalex.org/I33800924"]},{"id":"https://openalex.org/I4210114681","display_name":"National Institute for Research and Development in Informatics - ICI Bucharest","ror":"https://ror.org/028rq5v79","country_code":"RO","type":"facility","lineage":["https://openalex.org/I4210114681"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Florin Pop","raw_affiliation_strings":["National University of Science and Technology Politehnica, National Institute for Research and Development in Informatics (ICI), Academy of Romanian Scientists,Bucharest,Romania","National University of Science and Technology Politehnica, National Institute for Research and Development in Informatics (ICI), Academy of Romanian Scientists, Bucharest, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Science and Technology Politehnica, National Institute for Research and Development in Informatics (ICI), Academy of Romanian Scientists,Bucharest,Romania","institution_ids":["https://openalex.org/I33800924","https://openalex.org/I4210114681"]},{"raw_affiliation_string":"National University of Science and Technology Politehnica, National Institute for Research and Development in Informatics (ICI), Academy of Romanian Scientists, Bucharest, Romania","institution_ids":["https://openalex.org/I33800924","https://openalex.org/I4210114681"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1632,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5670003,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"85","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9876999855041504,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9876999855041504,"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/T10860","display_name":"Speech and Audio Processing","score":0.9861999750137329,"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/T12031","display_name":"Speech and dialogue systems","score":0.9653000235557556,"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":0.7781689763069153},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6869587302207947},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5930547118186951},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5367606282234192},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5105241537094116},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.48003116250038147},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47167548537254333},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.4606727361679077},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4584718346595764},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4431447684764862},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41154178977012634},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4030543863773346}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7781689763069153},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6869587302207947},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5930547118186951},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5367606282234192},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5105241537094116},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.48003116250038147},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47167548537254333},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.4606727361679077},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4584718346595764},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4431447684764862},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41154178977012634},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4030543863773346},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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":1,"locations":[{"id":"doi:10.1109/roedunet60162.2023.10274921","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/roedunet60162.2023.10274921","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 22nd RoEduNet Conference: Networking in Education and Research (RoEduNet)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1545214685","https://openalex.org/W2042659457","https://openalex.org/W2108819501","https://openalex.org/W2800448574","https://openalex.org/W2809254203","https://openalex.org/W3167533889","https://openalex.org/W3215704400","https://openalex.org/W4307303103","https://openalex.org/W4313515819","https://openalex.org/W4320063744"],"related_works":["https://openalex.org/W2358294942","https://openalex.org/W4367460280","https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"the":[3,43,54,65,88,109,112,151],"performance":[4,47,121],"of":[5,28,45,95,101,111,130,135,154],"four":[6],"speech/voice":[7],"activity":[8],"detection":[9],"(VAD)":[10],"models,":[11],"namely":[12],"SpeechBrain,":[13],"Picovoice,":[14],"InaSpeechSegmenter":[15],"and":[16,30,48,56,67,73,97,132,157,174],"WebRTC,":[17],"is":[18,34],"compared":[19],"using":[20],"data":[21],"collected":[22],"from":[23],"KAIST":[24],"(Korea":[25],"Advanced":[26],"Institute":[27],"Science":[29],"Technology).":[31],"The":[32,61,81,123],"goal":[33],"to":[35,77,108,141,169],"develop":[36,175],"an":[37,91],"improved":[38,124],"VAD":[39,114,155,172],"model":[40,72,125],"based":[41],"on":[42,53,64],"analysis":[44],"SpeechBrain\u2019s":[46],"provide":[49],"a":[50,98,127],"detailed":[51],"perspective":[52],"differences":[55],"similarities":[57],"between":[58],"these":[59],"models.":[60],"study":[62],"focuses":[63],"technologies":[66],"algorithms":[68],"used":[69,168],"by":[70],"each":[71],"utilizes":[74],"experimental":[75,82],"methods":[76],"evaluate":[78],"their":[79,158],"performance.":[80],"results":[83],"show":[84],"that":[85],"SpeechBrain":[86],"performs":[87],"best,":[89],"with":[90],"average":[92],"recall":[93,128],"value":[94,100,129,134],"0.97":[96],"precision":[99,133],"0.96.":[102],"Our":[103],"research":[104,165],"endeavors":[105],"have":[106],"led":[107],"refinement":[110],"existing":[113],"model,":[115],"resulting":[116],"in":[117,160],"even":[118],"more":[119,176],"compelling":[120],"metrics.":[122],"achieves":[126],"0.98":[131],"0.97,":[136],"signifying":[137],"its":[138],"enhanced":[139],"capability":[140],"accurately":[142],"detect":[143],"speech":[144,178],"activity.":[145],"These":[146],"findings":[147],"hold":[148],"promise":[149],"for":[150],"future":[152,171],"advancement":[153],"models":[156,173],"application":[159],"various":[161],"speech-processing":[162],"domains.":[163],"This":[164],"can":[166],"be":[167],"enhance":[170],"advanced":[177],"processing":[179],"applications.":[180]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
