{"id":"https://openalex.org/W3135241621","doi":"https://doi.org/10.1109/icassp39728.2021.9415081","title":"A Hybrid CNN-BiLSTM Voice Activity Detector","display_name":"A Hybrid CNN-BiLSTM Voice Activity Detector","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3135241621","doi":"https://doi.org/10.1109/icassp39728.2021.9415081","mag":"3135241621"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9415081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9415081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.03529","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038747889","display_name":"Nicholas I. Wilkinson","orcid":"https://orcid.org/0009-0009-5245-231X"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Nicholas Wilkinson","raw_affiliation_strings":["Stellenbosch University,Department of Electrical and Electronic Engineering,South Africa","StellenBosch University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stellenbosch University,Department of Electrical and Electronic Engineering,South Africa","institution_ids":["https://openalex.org/I26092322"]},{"raw_affiliation_string":"StellenBosch University","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050849172","display_name":"Thomas Niesler","orcid":"https://orcid.org/0000-0002-7341-1017"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Thomas Niesler","raw_affiliation_strings":["Stellenbosch University,Department of Electrical and Electronic Engineering,South Africa","StellenBosch University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stellenbosch University,Department of Electrical and Electronic Engineering,South Africa","institution_ids":["https://openalex.org/I26092322"]},{"raw_affiliation_string":"StellenBosch University","institution_ids":["https://openalex.org/I26092322"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I26092322"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6803","last_page":"6807"},"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":0.9998000264167786,"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":0.9997000098228455,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.8659037351608276},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7073827981948853},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6307342052459717},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5800549387931824},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5553101897239685},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5027174949645996},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.492738276720047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4556884467601776},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4108758568763733},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3952408730983734},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3786105513572693},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10776916146278381}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.8659037351608276},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7073827981948853},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6307342052459717},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5800549387931824},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5553101897239685},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5027174949645996},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.492738276720047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4556884467601776},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4108758568763733},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3952408730983734},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3786105513572693},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10776916146278381},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9415081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9415081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2103.03529","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.03529","pdf_url":"https://arxiv.org/pdf/2103.03529","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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3135241621","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2103.03529.pdf","pdf_url":null,"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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2103.03529","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.03529","pdf_url":null,"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":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/d265-4628","is_oa":true,"landing_page_url":"https://doi.org/10.17023/d265-4628","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.03529","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.03529","pdf_url":"https://arxiv.org/pdf/2103.03529","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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334105","display_name":"Center for High Performance Computing","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3135241621.pdf","grobid_xml":"https://content.openalex.org/works/W3135241621.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1509818672","https://openalex.org/W1600744878","https://openalex.org/W1985242443","https://openalex.org/W2048497537","https://openalex.org/W2098265087","https://openalex.org/W2100555417","https://openalex.org/W2101357962","https://openalex.org/W2108819501","https://openalex.org/W2129120544","https://openalex.org/W2135780429","https://openalex.org/W2167516348","https://openalex.org/W2171875099","https://openalex.org/W2194775991","https://openalex.org/W2197404611","https://openalex.org/W2406262283","https://openalex.org/W2513345070","https://openalex.org/W2526050071","https://openalex.org/W2641889749","https://openalex.org/W2792351646","https://openalex.org/W2885307078","https://openalex.org/W2964121744","https://openalex.org/W2972473987","https://openalex.org/W3017050142","https://openalex.org/W3018868673","https://openalex.org/W3140140631","https://openalex.org/W6631190155","https://openalex.org/W6680237693","https://openalex.org/W6740195615","https://openalex.org/W6776372148"],"related_works":["https://openalex.org/W3091889904","https://openalex.org/W2907088867","https://openalex.org/W3182611303","https://openalex.org/W3094333918","https://openalex.org/W2991443958","https://openalex.org/W3098167281","https://openalex.org/W2486148475","https://openalex.org/W3159298738","https://openalex.org/W3010835472","https://openalex.org/W3023943564","https://openalex.org/W3013431865","https://openalex.org/W3109677641","https://openalex.org/W3000291594","https://openalex.org/W2887447938","https://openalex.org/W2179596243","https://openalex.org/W2167360335","https://openalex.org/W2246760854","https://openalex.org/W3202341739","https://openalex.org/W2889847962","https://openalex.org/W2582144945"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,55,84,89,158],"new":[4],"hybrid":[5],"architecture":[6,42],"for":[7],"voice":[8],"activity":[9],"detection":[10],"(VAD)":[11],"incorporating":[12],"both":[13],"convolutional":[14],"neural":[15],"network":[16],"(CNN)":[17],"and":[18,69,75],"bidirectional":[19],"long":[20],"short-term":[21],"memory":[22],"(BiLSTM)":[23],"layers":[24,129,137],"trained":[25,124],"in":[26,43,49,54,164],"an":[27,144],"end-to-end":[28],"manner.":[29],"In":[30],"addition,":[31],"we":[32],"focus":[33],"specifically":[34],"on":[35,104,119,141],"optimising":[36],"the":[37,66,70,105,147],"computational":[38],"efficiency":[39],"of":[40,83,150],"our":[41,98,152],"order":[44],"to":[45,64,88,132],"deliver":[46],"robust":[47],"performance":[48,81],"difficult":[50,165],"in-the-wild":[51],"noise":[52,166],"conditions":[53],"severely":[56],"under-resourced":[57],"setting.":[58],"Nested":[59],"k-fold":[60],"cross-validation":[61],"was":[62,93],"used":[63],"explore":[65],"hyperparameter":[67],"space,":[68],"trade-off":[71],"between":[72],"optimal":[73,116,126],"parameters":[74,117],"model":[76],"size":[77],"is":[78],"discussed.":[79],"The":[80],"effect":[82],"BiLSTM":[85,128],"layer":[86,92],"compared":[87],"unidirectional":[90,136],"LSTM":[91],"also":[94],"considered.":[95],"We":[96,108],"compare":[97],"systems":[99],"with":[100,114,121,125],"three":[101],"established":[102],"baselines":[103],"AVA-Speech":[106],"dataset.":[107],"find":[109],"that":[110],"significantly":[111],"smaller":[112],"models":[113,123],"near":[115],"perform":[118],"par":[120],"larger":[122,160],"parameters.":[127],"were":[130],"shown":[131],"improve":[133],"accuracy":[134],"over":[135],"by":[138],"\u22482%":[139],"absolute":[140],"average.":[142],"With":[143],"area":[145],"under":[146],"curve":[148],"(AUC)":[149],"0.951,":[151],"system":[153],"outperforms":[154],"all":[155],"baselines,":[156],"including":[157],"much":[159],"ResNet":[161],"system,":[162],"particularly":[163],"conditions.":[167]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}