{"id":"https://openalex.org/W2578422401","doi":"https://doi.org/10.1145/3015166.3015207","title":"Vowel based Voice Activity Detection with LSTM Recurrent Neural Network","display_name":"Vowel based Voice Activity Detection with LSTM Recurrent Neural Network","publication_year":2016,"publication_date":"2016-11-21","ids":{"openalex":"https://openalex.org/W2578422401","doi":"https://doi.org/10.1145/3015166.3015207","mag":"2578422401"},"language":"en","primary_location":{"id":"doi:10.1145/3015166.3015207","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3015166.3015207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Conference on Signal Processing Systems","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/A5100710223","display_name":"Juntae Kim","orcid":"https://orcid.org/0000-0003-3344-4591"},"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":"Juntae Kim","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST), Daehak-ro, Yuseong-gu, Daejeon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST), Daehak-ro, Yuseong-gu, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101745218","display_name":"Jaeseok Kim","orcid":"https://orcid.org/0000-0002-2533-9292"},"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":"Jaeseok Kim","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST), Daehak-ro, Yuseong-gu, Daejeon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST), Daehak-ro, Yuseong-gu, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048891246","display_name":"Seunghyung Lee","orcid":"https://orcid.org/0000-0003-0914-9613"},"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":"Seunghyung Lee","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST), Daehak-ro, Yuseong-gu, Daejeon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST), Daehak-ro, Yuseong-gu, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056435660","display_name":"Jinuk Park","orcid":"https://orcid.org/0000-0002-9436-9639"},"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":"Jinuk Park","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST), Daehak-ro, Yuseong-gu, Daejeon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST), Daehak-ro, Yuseong-gu, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046372250","display_name":"Minsoo Hahn","orcid":"https://orcid.org/0000-0003-1953-6078"},"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":"Minsoo Hahn","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST), Daehak-ro, Yuseong-gu, Daejeon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST), Daehak-ro, Yuseong-gu, Daejeon, Republic of 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":1.0994,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.7912862,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"134","last_page":"137"},"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":0.9998000264167786,"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":0.9995999932289124,"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/recurrent-neural-network","display_name":"Recurrent neural network","score":0.8614234328269958},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8342595100402832},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8271591663360596},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.7033383846282959},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6149131059646606},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5681708455085754},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5296069383621216},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49012717604637146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46270397305488586},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4310040771961212},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3697221279144287},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3218435049057007},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.13258615136146545}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.8614234328269958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8342595100402832},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8271591663360596},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.7033383846282959},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6149131059646606},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5681708455085754},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5296069383621216},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49012717604637146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46270397305488586},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4310040771961212},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3697221279144287},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3218435049057007},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.13258615136146545},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3015166.3015207","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3015166.3015207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Conference on Signal Processing Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5199999809265137,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W36345725","https://openalex.org/W1580555281","https://openalex.org/W1974387177","https://openalex.org/W1985242443","https://openalex.org/W1990449877","https://openalex.org/W2020141429","https://openalex.org/W2023582935","https://openalex.org/W2062227835","https://openalex.org/W2095296829","https://openalex.org/W2098265087","https://openalex.org/W2101357962","https://openalex.org/W2117468249","https://openalex.org/W2126693545","https://openalex.org/W2129120544","https://openalex.org/W2147568880","https://openalex.org/W2149053750","https://openalex.org/W2197404611","https://openalex.org/W2271840356","https://openalex.org/W2293634267","https://openalex.org/W2407022425","https://openalex.org/W2915722758","https://openalex.org/W3007258144","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W2294333436","https://openalex.org/W2653598178","https://openalex.org/W2373767407","https://openalex.org/W3110551121","https://openalex.org/W3160071434","https://openalex.org/W2131486661","https://openalex.org/W4200596008"],"abstract_inverted_index":{"Voice":[0],"activity":[1],"detection":[2,155],"(VAD)":[3],"determines":[4],"whether":[5],"the":[6,35,40,52,97,110,127,144],"incoming":[7],"signal":[8],"segments":[9],"are":[10,63],"speech":[11,36,50,56,68],"or":[12],"noiseand":[13],"is":[14,94],"an":[15],"important":[16],"technique":[17],"in":[18,30,71,143],"almost":[19],"all":[20],"of":[21,55,126,130],"speech-related":[22],"applications.":[23],"In":[24],"order":[25,72],"to":[26,45,65,73,96,100,112,133,148],"improve":[27],"VAD":[28,83,145,151],"performance":[29],"various":[31],"noise":[32],"environments,":[33],"characterizing":[34],"feature":[37],"has":[38],"been":[39],"most":[41],"crucial":[42],"issue":[43],"up":[44],"date.":[46],"Among":[47],"several":[48],"proposed":[49,136],"features,":[51],"context":[53,103],"information":[54,104],"through":[57,105],"time":[58],"and":[59],"vowel":[60,81,114,154],"sound":[61],"characteristics":[62],"known":[64,95],"current":[66],"state-of-the-art":[67],"features.":[69],"Therefore,":[70],"reflect":[74],"both":[75],"on":[76],"these":[77],"merits,":[78],"we":[79],"propose":[80],"based":[82,150],"by":[84],"Long":[85],"short":[86],"term":[87],"memory":[88],"recurrent":[89],"neural":[90],"network":[91],"(LSTM-RNN).":[92],"LSTM-RNN":[93,111,120,149],"powerful":[98],"model":[99],"capture":[101],"dynamical":[102],"time.":[106],"Moreover,":[107],"with":[108],"teaching":[109],"only":[113,142],"sounds":[115],"rather":[116],"than":[117],"whole":[118],"speech,":[119],"can":[121],"learn":[122],"more":[123],"effectively":[124],"because":[125],"reduced":[128],"manifold":[129],"speech.":[131],"According":[132],"our":[134],"experiments,":[135],"method":[137],"shows":[138],"better":[139],"accuracy":[140],"not":[141],"task":[146],"compared":[147],"but":[152],"alsoa":[153],"task.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
