{"id":"https://openalex.org/W4387542704","doi":"https://doi.org/10.1145/3615834.3615835","title":"Compressed, Real-Time Voice Activity Detection with Open Source Implementation for Small Devices","display_name":"Compressed, Real-Time Voice Activity Detection with Open Source Implementation for Small Devices","publication_year":2023,"publication_date":"2023-09-21","ids":{"openalex":"https://openalex.org/W4387542704","doi":"https://doi.org/10.1145/3615834.3615835"},"language":"en","primary_location":{"id":"doi:10.1145/3615834.3615835","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3615834.3615835","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 Workshop on Sensor-Based Activity Recognition and Artificial Intelligence","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/A5101568518","display_name":"Lasse R. Andersen","orcid":"https://orcid.org/0009-0006-4874-1109"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Lasse R. Andersen","raw_affiliation_strings":["Aalborg University, Denmark"],"affiliations":[{"raw_affiliation_string":"Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093045478","display_name":"Lukas J. Jacobsen","orcid":"https://orcid.org/0009-0000-5545-5465"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Lukas J. Jacobsen","raw_affiliation_strings":["Aalborg University, Denmark"],"affiliations":[{"raw_affiliation_string":"Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101897790","display_name":"David Campos","orcid":"https://orcid.org/0009-0009-3044-6584"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"David Campos","raw_affiliation_strings":["Aalborg University, Denmark"],"affiliations":[{"raw_affiliation_string":"Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101568518"],"corresponding_institution_ids":["https://openalex.org/I891191580"],"apc_list":null,"apc_paid":null,"fwci":0.196,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.45272986,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"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":0.9993000030517578,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.8734239339828491},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5708834528923035},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.539627730846405},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.501223087310791},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.49633413553237915},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.4809974133968353},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.449611634016037},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.44883036613464355},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4471759498119354},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.42136532068252563},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3982080817222595},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35986006259918213},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3398006558418274},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.23347878456115723},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13903114199638367},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10633519291877747}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8734239339828491},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5708834528923035},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.539627730846405},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.501223087310791},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.49633413553237915},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.4809974133968353},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.449611634016037},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.44883036613464355},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4471759498119354},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.42136532068252563},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3982080817222595},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35986006259918213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3398006558418274},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.23347878456115723},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13903114199638367},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10633519291877747},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3615834.3615835","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3615834.3615835","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 Workshop on Sensor-Based Activity Recognition and Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/883c4e1f-266c-4e8a-b61c-1339b87b9ebc","is_oa":false,"landing_page_url":"https://vbn.aau.dk/da/publications/883c4e1f-266c-4e8a-b61c-1339b87b9ebc","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Andersen , L R , Jacobsen , L J &amp; Campos , D 2023 , Compressed, Real-Time Voice Activity Detection with Open Source Implementation for Small Devices. in D J C Matthies , M Grzegorzek , A Kuijper &amp; H Leutheuser (eds) , iWOAR 2023 - 8th International Workshop on Sensor-based Activity Recognition and Artificial Intelligence, Proceedings . , 1 , pp. 1:1-1:10 , 8th international Workshop on Sensor-Based Activity Recognition and Artificial Intelligence , L\u00fcbeck , Germany , 21/09/2023 . https://doi.org/10.1145/3615834.3615835","raw_type":"contributionToPeriodical"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1578856370","https://openalex.org/W2044893557","https://openalex.org/W2108289863","https://openalex.org/W2398020690","https://openalex.org/W2788770315","https://openalex.org/W2792351646","https://openalex.org/W2912500072","https://openalex.org/W2997591727","https://openalex.org/W3034021666","https://openalex.org/W3160747466","https://openalex.org/W3184606595","https://openalex.org/W4245325600","https://openalex.org/W4310147199","https://openalex.org/W6823467933"],"related_works":["https://openalex.org/W2341492732","https://openalex.org/W3187193180","https://openalex.org/W106542691","https://openalex.org/W1699080303","https://openalex.org/W4297799326","https://openalex.org/W2977327189","https://openalex.org/W4225315139","https://openalex.org/W4385881881","https://openalex.org/W3128402741","https://openalex.org/W2078418570"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,12,114],"real-time":[4],"voice":[5],"activity":[6],"detection":[7],"(VAD)":[8],"system":[9,23,45,72,101,156],"that":[10,68],"utilizes":[11],"compressed":[13,129],"convolutional":[14],"neural":[15],"network":[16],"(CNN)":[17],"model.":[18],"On":[19],"general-purpose":[20],"computers,":[21],"the":[22,29,44,59,65,69,77,84,89,98,106,110,122,134,149,153,168,173],"is":[24,46,51,73,125,157],"capable":[25,126],"of":[26,31,55,64,82,91,105,127,133,152,172],"accurately":[27],"classifying":[28],"presence":[30],"speech":[32],"in":[33,58,80,159],"audio":[34],"with":[35],"low":[36],"latency.":[37],"Whereas,":[38],"when":[39],"implemented":[40],"on":[41,113,139],"small":[42,140],"devices,":[43],"showing":[47],"higher":[48],"latency,":[49],"which":[50],"presumably":[52],"an":[53,74,103],"indication":[54],"high-load":[56],"computations":[57],"preprocessing":[60],"steps.":[61],"The":[62],"results":[63],"evaluation":[66,95],"indicate":[67],"proposed":[70,99,123,154],"VAD":[71,100,147,155],"improvement":[75],"over":[76],"existing":[78,145],"solutions,":[79,148],"terms":[81],"reducing":[83],"model":[85,112],"size":[86],"and":[87,116,161,170],"improving":[88],"level":[90],"accuracy":[92],"among":[93],"different":[94,115],"metrics.":[96],"Furthermore,":[97],"offers":[102],"extension":[104],"applicability":[107],"by":[108],"training":[109],"CNN":[111],"more":[117],"diverse":[118],"data":[119],"set.":[120],"Moreover,":[121],"architecture":[124],"being":[128],"to":[130,144],"approximately":[131],"one-eleventh":[132],"size,":[135],"facilitating":[136],"eventual":[137],"deployment":[138],"devices.":[141],"In":[142],"contrast":[143],"closed":[146],"entire":[150],"pipeline":[151],"developed":[158],"Python":[160],"made":[162],"available":[163],"as":[164],"open":[165],"source,":[166],"ensuring":[167],"verifiability":[169],"accessibility":[171],"work.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}
