{"id":"https://openalex.org/W2772561196","doi":"https://doi.org/10.1109/icsda.2017.8384446","title":"Linear-scale filterbank for deep neural network-based voice activity detection","display_name":"Linear-scale filterbank for deep neural network-based voice activity detection","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W2772561196","doi":"https://doi.org/10.1109/icsda.2017.8384446","mag":"2772561196"},"language":"en","primary_location":{"id":"doi:10.1109/icsda.2017.8384446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsda.2017.8384446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 20th Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I/O Systems and Assessment (O-COCOSDA)","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/A5101457226","display_name":"Youngmoon Jung","orcid":"https://orcid.org/0000-0002-4321-379X"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngmoon Jung","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046397537","display_name":"Younggwan Kim","orcid":"https://orcid.org/0000-0003-2053-8521"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Younggwan Kim","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043111329","display_name":"Hyungjun Lim","orcid":"https://orcid.org/0000-0002-0015-4259"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyungjun Lim","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066573438","display_name":"Hoirin Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hoirin Kim","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":1.6818,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.86042861,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9993000030517578,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8707322478294373},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.8046751022338867},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7045515775680542},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.645469605922699},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6273612380027771},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6103826761245728},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6078404784202576},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5522739887237549},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5430353283882141},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5142226219177246},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46226823329925537},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4121188223361969},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.33711788058280945},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08496904373168945}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8707322478294373},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.8046751022338867},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7045515775680542},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.645469605922699},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6273612380027771},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6103826761245728},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6078404784202576},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5522739887237549},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5430353283882141},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5142226219177246},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46226823329925537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4121188223361969},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.33711788058280945},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08496904373168945},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsda.2017.8384446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsda.2017.8384446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 20th Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I/O Systems and Assessment (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1985242443","https://openalex.org/W1999454387","https://openalex.org/W2034329102","https://openalex.org/W2059203007","https://openalex.org/W2116764165","https://openalex.org/W2129120544","https://openalex.org/W2138029428","https://openalex.org/W2157825442","https://openalex.org/W2171875099","https://openalex.org/W2197404611","https://openalex.org/W2394998899","https://openalex.org/W2401364490","https://openalex.org/W2406262283","https://openalex.org/W2408468399","https://openalex.org/W2511222575","https://openalex.org/W2513345070","https://openalex.org/W6631943919","https://openalex.org/W6713037448","https://openalex.org/W6713752823"],"related_works":["https://openalex.org/W2766680336","https://openalex.org/W2133320490","https://openalex.org/W4289830142","https://openalex.org/W1497065097","https://openalex.org/W2125446021","https://openalex.org/W3150393935","https://openalex.org/W2980055100","https://openalex.org/W2186790562","https://openalex.org/W2548564146","https://openalex.org/W2756038079"],"abstract_inverted_index":{"Voice":[0],"activity":[1],"detection":[2],"(VAD)":[3],"is":[4,19,72],"an":[5,24],"important":[6,89],"preprocessing":[7],"module":[8],"in":[9,48,60,87,94,101,112],"many":[10],"speech":[11,53],"applications.":[12],"Choosing":[13],"appropriate":[14],"features":[15,32],"and":[16,23,39,147,164],"model":[17],"structures":[18],"a":[20,99,117,160],"significant":[21],"challenge":[22],"active":[25],"area":[26],"of":[27,67,85,157,162,170],"current":[28],"VAD":[29,49,122,145],"research.":[30],"Mel-scale":[31],"such":[33],"as":[34,50,52],"Mel-frequency":[35],"cepstral":[36],"coefficients":[37],"(MFCCs)":[38],"log":[40,135],"Mel-filterbank":[41],"(LMFB)":[42],"energies":[43],"have":[44],"been":[45],"widely":[46],"used":[47,141],"well":[51],"recognition.":[54],"The":[55],"reason":[56],"for":[57,82,142,154],"feature":[58],"extraction":[59],"Mel-":[61,109],"frequency":[62,97,102],"scale":[63],"to":[64],"be":[65,140],"one":[66],"the":[68,95,108,131,143,152,171],"most":[69],"popular":[70],"methods":[71],"that":[73,130],"it":[74],"mimics":[75],"how":[76],"human":[77],"ears":[78],"process":[79],"sound.":[80],"However,":[81],"certain":[83,155],"types":[84,156],"sound,":[86],"which":[88],"characteristics":[90],"are":[91],"reflected":[92],"more":[93,105],"high":[96],"range,":[98],"linear-scale":[100,125,132],"may":[103],"provide":[104],"information":[106],"than":[107,151],"scale.":[110],"Therefore,":[111],"this":[113],"paper,":[114],"we":[115],"propose":[116],"deep":[118],"neural":[119],"network":[120],"(DNN)-based":[121],"system":[123,146],"using":[124],"feature.":[126],"This":[127],"study":[128],"shows":[129,148],"feature,":[133],"especially":[134],"linear-filterbank":[136],"(LLFB)":[137],"energy,":[138],"can":[139,166],"DNN-based":[144],"better":[149],"performance":[150],"LMFB":[153,163],"noise.":[158],"Moreover,":[159],"combination":[161],"LLFB":[165],"integrates":[167],"both":[168],"advantages":[169],"two":[172],"features.":[173]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}