{"id":"https://openalex.org/W3021500721","doi":"https://doi.org/10.21437/interspeech.2020-995","title":"Voice Activity Detection in the Wild via Weakly Supervised Sound Event Detection","display_name":"Voice Activity Detection in the Wild via Weakly Supervised Sound Event Detection","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3021500721","doi":"https://doi.org/10.21437/interspeech.2020-995","mag":"3021500721"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-995","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5012756702","display_name":"Yefei Chen","orcid":"https://orcid.org/0000-0003-1414-2045"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yefei Chen","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence SpeechLab, Department of Computer Science and Engineering AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence SpeechLab, Department of Computer Science and Engineering AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080154283","display_name":"Heinrich Dinkel","orcid":"https://orcid.org/0000-0003-4330-8980"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heinrich Dinkel","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence SpeechLab, Department of Computer Science and Engineering AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence SpeechLab, Department of Computer Science and Engineering AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081865665","display_name":"Mengyue Wu","orcid":"https://orcid.org/0000-0002-5599-8707"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyue Wu","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence SpeechLab, Department of Computer Science and Engineering AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence SpeechLab, Department of Computer Science and Engineering AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3665","last_page":"3669"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10860","display_name":"Speech 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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9970999956130981,"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/voice-activity-detection","display_name":"Voice activity detection","score":0.651123046875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.627105712890625},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5870156288146973},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5776672959327698},{"id":"https://openalex.org/keywords/detection-theory","display_name":"Detection theory","score":0.4308015704154968},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37581923604011536},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.30344992876052856},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.18946599960327148},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12973466515541077},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07642868161201477}],"concepts":[{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.651123046875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.627105712890625},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5870156288146973},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5776672959327698},{"id":"https://openalex.org/C137270730","wikidata":"https://www.wikidata.org/wiki/Q120811","display_name":"Detection theory","level":3,"score":0.4308015704154968},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37581923604011536},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.30344992876052856},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.18946599960327148},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12973466515541077},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07642868161201477},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-995","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W54887220","https://openalex.org/W1524333225","https://openalex.org/W1999454387","https://openalex.org/W2048497537","https://openalex.org/W2059203007","https://openalex.org/W2125838338","https://openalex.org/W2151484683","https://openalex.org/W2158698691","https://openalex.org/W2166637769","https://openalex.org/W2406262283","https://openalex.org/W2408239454","https://openalex.org/W2408468399","https://openalex.org/W2591013610","https://openalex.org/W2593116425","https://openalex.org/W2604490051","https://openalex.org/W2884011836","https://openalex.org/W2899771611","https://openalex.org/W2954975210","https://openalex.org/W2963610932","https://openalex.org/W2977846024","https://openalex.org/W2981728176","https://openalex.org/W3015190346","https://openalex.org/W3016059657","https://openalex.org/W3017521796","https://openalex.org/W3094550259","https://openalex.org/W3123940584","https://openalex.org/W3209073848","https://openalex.org/W4253573210","https://openalex.org/W4289329167"],"related_works":["https://openalex.org/W1856957993","https://openalex.org/W191108438","https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W249088392","https://openalex.org/W1966535600","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2131711534","https://openalex.org/W2559837139"],"abstract_inverted_index":{"Traditional":[0],"supervised":[1,44,66],"voice":[2],"activity":[3],"detection":[4],"(VAD)":[5],"methods":[6],"work":[7],"well":[8,148],"in":[9,18,26,63,125,134,141,172],"clean":[10,126],"and":[11,85,92,127],"controlled":[12],"scenarios,":[13],"with":[14],"performance":[15,124,169],"severely":[16],"degrading":[17],"real-world":[19,135,173],"applications.One":[20],"possible":[21],"bottleneck":[22],"is":[23,37,40],"that":[24,118],"speech":[25,91],"the":[27,95,159],"wild":[28],"contains":[29],"unpredictable":[30],"noise":[31],"types,":[32],"hence":[33],"frame-level":[34,144],"label":[35],"prediction":[36],"difficult,":[38],"which":[39,55],"required":[41],"for":[42,156],"traditional":[43,132],"VAD":[45,52,104],"training.In":[46],"contrast,":[47],"we":[48],"propose":[49],"a":[50,64,100,152],"general-purpose":[51],"(GPVAD)":[53],"framework,":[54],"can":[56,165],"be":[57],"easily":[58],"trained":[59,79],"from":[60],"noisy":[61],"data":[62],"weakly":[65],"fashion,":[67],"requiring":[68],"only":[69,89],"clip-level":[70,162],"labels.We":[71],"proposed":[72,120],"two":[73,96],"GP-VAD":[74],"models,":[75],"one":[76,86],"full":[77],"(GPV-F),":[78],"on":[80,107],"527":[81],"Audioset":[82],"sound":[83],"events,":[84],"binary":[87,161],"(GPV-B),":[88],"distinguishing":[90],"noise.We":[93],"evaluate":[94],"GPV":[97],"models":[98],"against":[99],"CRNN":[101],"based":[102],"standard":[103],"model":[105,164],"(VAD-C)":[106],"three":[108],"different":[109],"evaluation":[110,145],"protocols":[111],"(clean,":[112],"synthetic":[113,128],"noise,":[114],"real":[115],"data).Results":[116],"show":[117],"our":[119],"GPV-F":[121,137],"demonstrates":[122],"competitive":[123],"scenarios":[129],"compared":[130],"to":[131,170],"VAD-C.Further,":[133],"evaluation,":[136],"largely":[138],"outperforms":[139],"VAD-C":[140,171],"terms":[142],"of":[143],"metrics":[146],"as":[147,149],"segment-level":[150],"ones.With":[151],"much":[153],"lower":[154],"requirement":[155],"framelabeled":[157],"data,":[158],"naive":[160],"GPV-B":[163],"still":[166],"achieve":[167],"comparable":[168],"scenarios.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}