{"id":"https://openalex.org/W3153215492","doi":"https://doi.org/10.1109/taslp.2021.3073596","title":"Voice Activity Detection in the Wild: A Data-Driven Approach Using Teacher-Student Training","display_name":"Voice Activity Detection in the Wild: A Data-Driven Approach Using Teacher-Student Training","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3153215492","doi":"https://doi.org/10.1109/taslp.2021.3073596","mag":"3153215492"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3073596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3073596","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.04065","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"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":true,"raw_author_name":"Heinrich Dinkel","raw_affiliation_strings":["State Key Laboratory of Media Convergence Production Technology and Systems, Beijing, China","X-LANCE Lab, Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Media Convergence Production Technology and Systems, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"X-LANCE Lab, Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0003-1523-9631"},"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":"Shuai Wang","raw_affiliation_strings":["State Key Laboratory of Media Convergence Production Technology and Systems, Beijing, China","X-LANCE Lab, Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Media Convergence Production Technology and Systems, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"X-LANCE Lab, Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xuenan Xu","orcid":null},"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":"Xuenan Xu","raw_affiliation_strings":["State Key Laboratory of Media Convergence Production Technology and Systems, Beijing, China","X-LANCE Lab, Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Media Convergence Production Technology and Systems, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"X-LANCE Lab, Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"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":["State Key Laboratory of Media Convergence Production Technology and Systems, Beijing, China","X-LANCE Lab, Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Media Convergence Production Technology and Systems, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"X-LANCE Lab, Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":null,"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":["State Key Laboratory of Media Convergence Production Technology and Systems, Beijing, China","X-LANCE Lab, Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Media Convergence Production Technology and Systems, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"X-LANCE Lab, Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":4.1655,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.94950508,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"29","issue":null,"first_page":"1542","last_page":"1555"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.6338000297546387,"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":0.6338000297546387,"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":0.2549000084400177,"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":0.016499999910593033,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.6607000231742859},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6366000175476074},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5464000105857849},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.5281000137329102},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4374000132083893},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.436599999666214},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.42969998717308044},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3928999900817871}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6966999769210815},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6607000231742859},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6366000175476074},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6229000091552734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5730999708175659},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5464000105857849},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.5281000137329102},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48089998960494995},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4374000132083893},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.436599999666214},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.42969998717308044},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3928999900817871},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3127000033855438},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.296099990606308},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.2930000126361847},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2791000008583069},{"id":"https://openalex.org/C51432778","wikidata":"https://www.wikidata.org/wiki/Q1259145","display_name":"Independent component analysis","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2021.3073596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3073596","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2105.04065","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.04065","pdf_url":"https://arxiv.org/pdf/2105.04065","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.04065","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.04065","pdf_url":"https://arxiv.org/pdf/2105.04065","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3420185677","display_name":null,"funder_award_id":"61901265","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1985242443","https://openalex.org/W1999454387","https://openalex.org/W2023582935","https://openalex.org/W2032362923","https://openalex.org/W2032474878","https://openalex.org/W2048497537","https://openalex.org/W2056608640","https://openalex.org/W2059203007","https://openalex.org/W2106214098","https://openalex.org/W2109000787","https://openalex.org/W2115008841","https://openalex.org/W2129120544","https://openalex.org/W2141102245","https://openalex.org/W2142170306","https://openalex.org/W2151484683","https://openalex.org/W2158698691","https://openalex.org/W2159105055","https://openalex.org/W2166637769","https://openalex.org/W2394998899","https://openalex.org/W2404617565","https://openalex.org/W2408239454","https://openalex.org/W2408468399","https://openalex.org/W2512215050","https://openalex.org/W2593116425","https://openalex.org/W2726515241","https://openalex.org/W2738707637","https://openalex.org/W2791616807","https://openalex.org/W2798158991","https://openalex.org/W2808631503","https://openalex.org/W2889192039","https://openalex.org/W2889224635","https://openalex.org/W2936774411","https://openalex.org/W2954461214","https://openalex.org/W2954930777","https://openalex.org/W2963022469","https://openalex.org/W2963610932","https://openalex.org/W2963723765","https://openalex.org/W2972643142","https://openalex.org/W2972861996","https://openalex.org/W2981087920","https://openalex.org/W2981728176","https://openalex.org/W3015190346","https://openalex.org/W3016059657","https://openalex.org/W3024085360","https://openalex.org/W3094550259","https://openalex.org/W3094793410","https://openalex.org/W3096625841","https://openalex.org/W3124216180","https://openalex.org/W6610623297","https://openalex.org/W6631362777","https://openalex.org/W6688816777","https://openalex.org/W6713752823","https://openalex.org/W6753516609","https://openalex.org/W6766978945"],"related_works":[],"abstract_inverted_index":{"Voice":[0],"activity":[1],"detection":[2],"is":[3,67,162],"an":[4,25,139],"essential":[5],"pre-processing":[6],"component":[7],"for":[8,63,81,90],"speech-related":[9],"tasks":[10],"such":[11],"as":[12],"automatic":[13],"speech":[14],"recognition":[15],"(ASR).":[16],"Traditional":[17],"supervised":[18,64,193],"VAD":[19,48,65,194],"systems":[20,49,66],"obtain":[21],"frame-level":[22,132],"labels":[23,97],"from":[24],"ASR":[26,36],"pipeline":[27],"by":[28],"using,":[29],"e.g.,":[30],"a":[31,60,77,116,120,135],"Hidden":[32],"Markov":[33],"model.":[34],"These":[35],"models":[37,147],"are":[38,101,154],"commonly":[39],"trained":[40,52,148],"on":[41,53,119,138,149,166],"clean":[42,54],"and":[43,86,170,181,192],"fully":[44],"transcribed":[45],"data,":[46],"limiting":[47],"to":[50,134,151],"be":[51],"or":[55],"synthetically":[56],"noised":[57,180],"datasets.":[58],"Therefore,":[59],"major":[61],"challenge":[62],"their":[68],"generalization":[69],"towards":[70],"noisy,":[71],"real-world":[72,171,182],"data.":[73,172],"This":[74],"work":[75],"proposes":[76],"data-driven":[78],"teacher-student":[79],"approach":[80,113,161,188],"VAD,":[82],"which":[83],"utilizes":[84],"vast":[85],"unconstrained":[87],"audio":[88],"data":[89],"training.":[91],"Unlike":[92],"previous":[93],"approaches,":[94],"only":[95],"weak":[96],"during":[98],"teacher":[99,117,130],"training":[100],"required,":[102],"enabling":[103],"the":[104,129],"utilization":[105],"of":[106,145],"any":[107],"real-world,":[108],"potentially":[109],"noisy":[110],"dataset.":[111,142],"Our":[112,160],"firstly":[114],"trains":[115],"model":[118,137],"source":[121],"dataset":[122],"(Audioset)":[123],"using":[124],"clip-level":[125],"supervision.":[126],"After":[127],"training,":[128],"provides":[131],"guidance":[133],"student":[136,146],"unlabeled,":[140],"target":[141],"A":[143],"multitude":[144],"mid-":[150],"large-sized":[152],"datasets":[153],"investigated":[155],"(Audioset,":[156],"Voxceleb,":[157],"NIST":[158],"SRE).":[159],"then":[163],"respectively":[164],"evaluated":[165],"clean,":[167],"artificially":[168,179],"noised,":[169],"We":[173],"observe":[174],"significant":[175],"performance":[176],"gains":[177],"in":[178],"scenarios.":[183],"Lastly,":[184],"we":[185],"compare":[186],"our":[187,197],"against":[189],"other":[190],"unsupervised":[191],"methods,":[195],"demonstrating":[196],"method's":[198],"superiority.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":4}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2021-04-26T00:00:00"}