{"id":"https://openalex.org/W4284709148","doi":"https://doi.org/10.21437/interspeech.2022-10033","title":"Adversarial Multi-Task Deep Learning for Noise-Robust Voice Activity Detection with Low Algorithmic Delay","display_name":"Adversarial Multi-Task Deep Learning for Noise-Robust Voice Activity Detection with Low Algorithmic Delay","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4284709148","doi":"https://doi.org/10.21437/interspeech.2022-10033"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10033","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10033","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2207.01691.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109177077","display_name":"Claus Larsen","orcid":null},"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":"Claus Larsen","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090047862","display_name":"Peter Koch","orcid":"https://orcid.org/0000-0002-5328-7127"},"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":"Peter Koch","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090108098","display_name":"Zheng\u2010Hua Tan","orcid":"https://orcid.org/0000-0001-6856-8928"},"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":"Zheng-Hua Tan","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I891191580"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3759","last_page":"3763"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9980000257492065,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9947999715805054,"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":0.8198820352554321},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.7937607169151306},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.7190348505973816},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6962123513221741},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6172550916671753},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6069992780685425},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5126017928123474},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.46327802538871765},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4443071782588959},{"id":"https://openalex.org/keywords/degradation","display_name":"Degradation (telecommunications)","score":0.4426155686378479},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4319164454936981},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42763084173202515},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4125766158103943},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33337244391441345},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.32187992334365845},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09937572479248047},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07776331901550293}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8198820352554321},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.7937607169151306},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7190348505973816},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6962123513221741},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6172550916671753},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6069992780685425},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5126017928123474},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46327802538871765},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4443071782588959},{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.4426155686378479},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4319164454936981},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42763084173202515},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4125766158103943},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33337244391441345},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.32187992334365845},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09937572479248047},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07776331901550293},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2022-10033","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10033","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/55e2d6a5-57f1-4ce1-b881-6b3aaccfdc3c","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/55e2d6a5-57f1-4ce1-b881-6b3aaccfdc3c","pdf_url":"https://arxiv.org/pdf/2207.01691.pdf","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Larsen , C M , Koch , P & Tan , Z-H 2022 , Adversarial Multi-Task Deep Learning for Noise-Robust Voice Activity Detection with Low Algorithmic Delay . in Interspeech 2022 . Proceedings of the International Conference on Spoken Language Processing , pp. 3759-3763 , Interspeech 2022 , Incheon , Korea, Republic of , 18/09/2022 . https://doi.org/10.21437/Interspeech.2022-10033","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:publications/55e2d6a5-57f1-4ce1-b881-6b3aaccfdc3c","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/55e2d6a5-57f1-4ce1-b881-6b3aaccfdc3c","pdf_url":"https://arxiv.org/pdf/2207.01691.pdf","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Larsen , C M , Koch , P & Tan , Z-H 2022 , Adversarial Multi-Task Deep Learning for Noise-Robust Voice Activity Detection with Low Algorithmic Delay . in Interspeech 2022 . Proceedings of the International Conference on Spoken Language Processing , pp. 3759-3763 , Interspeech 2022 , Incheon , Korea, Republic of , 18/09/2022 . https://doi.org/10.21437/Interspeech.2022-10033","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6000000238418579,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4284709148.pdf","grobid_xml":"https://content.openalex.org/works/W4284709148.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1563939609","https://openalex.org/W1677182931","https://openalex.org/W1985242443","https://openalex.org/W2007119422","https://openalex.org/W2023582935","https://openalex.org/W2148030532","https://openalex.org/W2289394825","https://openalex.org/W2510867321","https://openalex.org/W2513345070","https://openalex.org/W2550397165","https://openalex.org/W2557377817","https://openalex.org/W2586068394","https://openalex.org/W2889500840","https://openalex.org/W2954930777","https://openalex.org/W2962914040","https://openalex.org/W2995588677","https://openalex.org/W2998115938","https://openalex.org/W3036462239","https://openalex.org/W3110588169","https://openalex.org/W3127686677","https://openalex.org/W3163621198","https://openalex.org/W4210518348","https://openalex.org/W4287173589","https://openalex.org/W4295312788","https://openalex.org/W4297841774"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W4294771049","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W1523214805","https://openalex.org/W4411210718","https://openalex.org/W2168417340","https://openalex.org/W4229451372","https://openalex.org/W2113211312"],"abstract_inverted_index":{"Voice":[0,62],"Activity":[1,63],"Detection":[2],"(VAD)":[3],"is":[4,70,77,89,108,118,140,144,151],"an":[5,43,78],"important":[6,79],"pre-processing":[7],"step":[8],"in":[9,18,27,81,94,102,121,131],"a":[10,19,50],"wide":[11],"variety":[12],"of":[13,67,96],"speech":[14,26],"processing":[15],"systems.VAD":[16],"should":[17],"practical":[20],"application":[21],"be":[22],"able":[23],"to":[24,57,86,91,162],"detect":[25],"both":[28],"noisy":[29,103],"and":[30,125,137,142],"noise-free":[31],"environments,":[32,104],"while":[33,105],"not":[34,109],"introducing":[35],"significant":[36],"latency.In":[37],"this":[38],"work":[39],"we":[40],"propose":[41],"using":[42],"adversarial":[44,83,115],"multi-task":[45,84,116],"learning":[46,85,117],"method":[47,53],"when":[48,154],"training":[49,123],"supervised":[51],"VAD.The":[52],"has":[54],"been":[55],"applied":[56,120],"the":[58,65,68,87,106,122,133,147,156],"state-of-the-art":[59],"VAD":[60,69,148],"Waveform-based":[61],"Detection.Additionally":[64],"performance":[66,93,107,136,149],"investigated":[71],"under":[72],"different":[73],"algorithmic":[74,138,157],"delays,":[75],"which":[76],"factor":[80],"latency.Introducing":[82],"model":[88],"observed":[90,145],"increase":[92],"terms":[95],"Area":[97],"Under":[98],"Curve":[99],"(AUC),":[100],"particularly":[101],"degraded":[110],"at":[111],"higher":[112],"SNR":[113],"levels.The":[114],"only":[119,152],"phase":[124],"thus":[126],"introduces":[127],"no":[128],"additional":[129],"cost":[130],"testing.Furthermore":[132],"correlation":[134],"between":[135],"delays":[139],"investigated,":[141],"it":[143],"that":[146],"degradation":[150],"moderate":[153],"lowering":[155],"delay":[158],"from":[159],"398":[160],"ms":[161],"23":[163],"ms.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}