{"id":"https://openalex.org/W4372262623","doi":"https://doi.org/10.1109/icassp49357.2023.10096938","title":"SG-VAD: Stochastic Gates Based Speech Activity Detection","display_name":"SG-VAD: Stochastic Gates Based Speech Activity Detection","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372262623","doi":"https://doi.org/10.1109/icassp49357.2023.10096938"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096938","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096938","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5088094106","display_name":"Jonathan Svirsky","orcid":null},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Jonathan Svirsky","raw_affiliation_strings":["Bar-Ilan University,Faculty of Engineering,Ramat-Gan,Israel,5290002"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bar-Ilan University,Faculty of Engineering,Ramat-Gan,Israel,5290002","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053239679","display_name":"Ofir Lindenbaum","orcid":"https://orcid.org/0000-0002-5990-742X"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ofir Lindenbaum","raw_affiliation_strings":["Bar-Ilan University,Faculty of Engineering,Ramat-Gan,Israel,5290002"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bar-Ilan University,Faculty of Engineering,Ramat-Gan,Israel,5290002","institution_ids":["https://openalex.org/I13955877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8476,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.85935372,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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":0.6638317704200745},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6571859121322632},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5930379033088684},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3079710900783539}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6638317704200745},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6571859121322632},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5930379033088684},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3079710900783539}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096938","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096938","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2033875152","https://openalex.org/W2045956438","https://openalex.org/W2252254117","https://openalex.org/W2593116425","https://openalex.org/W2746314669","https://openalex.org/W2797583228","https://openalex.org/W2804802260","https://openalex.org/W2885307078","https://openalex.org/W2936774411","https://openalex.org/W2951732061","https://openalex.org/W2963855133","https://openalex.org/W2974231335","https://openalex.org/W3013492814","https://openalex.org/W3021500721","https://openalex.org/W3030437843","https://openalex.org/W3035089687","https://openalex.org/W3097906045","https://openalex.org/W3105512231","https://openalex.org/W3160747466","https://openalex.org/W3193786050","https://openalex.org/W3197042120","https://openalex.org/W4224926630","https://openalex.org/W4281554565","https://openalex.org/W4286890588","https://openalex.org/W4287120898","https://openalex.org/W4296068967","https://openalex.org/W4297841774","https://openalex.org/W6691726237","https://openalex.org/W6738768603","https://openalex.org/W6743428213","https://openalex.org/W6750665317","https://openalex.org/W6751300517","https://openalex.org/W6759872529","https://openalex.org/W6767671539","https://openalex.org/W6771467084","https://openalex.org/W6775574022","https://openalex.org/W6776837456","https://openalex.org/W6785840938","https://openalex.org/W6803098416","https://openalex.org/W6809845688","https://openalex.org/W6840516729"],"related_works":["https://openalex.org/W191108438","https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W249088392","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2559837139","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"We":[0,40,80,93],"propose":[1],"a":[2,10,21,26,36],"novel":[3],"voice":[4],"activity":[5],"detection":[6],"(VAD)":[7],"model":[8,18,43,57,99],"in":[9],"low-resource":[11],"environment.":[12],"Our":[13,56],"key":[14],"idea":[15],"is":[16,29],"to":[17,31,44],"VAD":[19],"as":[20],"denoising":[22],"task":[23],"and":[24,72,86,97],"construct":[25],"network":[27],"that":[28],"designed":[30],"identify":[32,46],"nuisance":[33],"features":[34,48],"for":[35],"speech":[37,54],"classification":[38],"task.":[39],"train":[41],"the":[42,51,63,68,77,90,95,98],"simultaneously":[45],"irrelevant":[47],"while":[49],"predicting":[50],"type":[52],"of":[53],"event.":[55],"contains":[58],"only":[59],"7.8K":[60],"parameters,":[61],"outperforms":[62],"previously":[64],"proposed":[65],"methods":[66],"on":[67,76,89],"AVA-Speech":[69],"evaluation":[70],"set,":[71],"provides":[73],"comparative":[74],"results":[75],"HAVIC":[78],"dataset.":[79],"present":[81],"its":[82],"architecture,":[83],"experimental":[84],"results,":[85],"ablation":[87],"study":[88],"model\u2019s":[91],"components.":[92],"publish":[94],"code":[96],"<sup":[100],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[101],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[102],".":[103]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}