{"id":"https://openalex.org/W3160984956","doi":"https://doi.org/10.1109/icassp39728.2021.9413961","title":"Self-Attentive VAD: Context-Aware Detection of Voice from Noise","display_name":"Self-Attentive VAD: Context-Aware Detection of Voice from Noise","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160984956","doi":"https://doi.org/10.1109/icassp39728.2021.9413961","mag":"3160984956"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5022353186","display_name":"Yong Rae Jo","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yong Rae Jo","raw_affiliation_strings":["Voithru Inc"],"affiliations":[{"raw_affiliation_string":"Voithru Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078428721","display_name":"Young Ki Moon","orcid":null},"institutions":[{"id":"https://openalex.org/I191879574","display_name":"Inha University","ror":"https://ror.org/01easw929","country_code":"KR","type":"education","lineage":["https://openalex.org/I191879574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Young Ki Moon","raw_affiliation_strings":["Voithru Inc","Inha University"],"affiliations":[{"raw_affiliation_string":"Voithru Inc","institution_ids":[]},{"raw_affiliation_string":"Inha University","institution_ids":["https://openalex.org/I191879574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102984975","display_name":"Won Ik Cho","orcid":"https://orcid.org/0000-0002-8882-9125"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Won Ik Cho","raw_affiliation_strings":["Seoul National University"],"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114032705","display_name":"Geun Sik Jo","orcid":null},"institutions":[{"id":"https://openalex.org/I191879574","display_name":"Inha University","ror":"https://ror.org/01easw929","country_code":"KR","type":"education","lineage":["https://openalex.org/I191879574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Geun Sik Jo","raw_affiliation_strings":["Inha University"],"affiliations":[{"raw_affiliation_string":"Inha University","institution_ids":["https://openalex.org/I191879574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5022353186"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.676,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.84151454,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6808","last_page":"6812"},"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":0.9998999834060669,"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":0.9995999932289124,"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":0.8444530963897705},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7781311273574829},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6117797493934631},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5062045454978943},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4793611168861389},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4418940842151642},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.43826743960380554},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.42566609382629395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4176979959011078}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8444530963897705},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7781311273574829},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6117797493934631},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5062045454978943},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4793611168861389},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4418940842151642},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.43826743960380554},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42566609382629395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4176979959011078},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W807203886","https://openalex.org/W1905983571","https://openalex.org/W1974387177","https://openalex.org/W1999454387","https://openalex.org/W2007119422","https://openalex.org/W2017608047","https://openalex.org/W2048497537","https://openalex.org/W2108819501","https://openalex.org/W2116520137","https://openalex.org/W2129120544","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2197404611","https://openalex.org/W2219249508","https://openalex.org/W2240641835","https://openalex.org/W2398020690","https://openalex.org/W2406262283","https://openalex.org/W2510670092","https://openalex.org/W2513345070","https://openalex.org/W2524365899","https://openalex.org/W2791616807","https://openalex.org/W2917416935","https://openalex.org/W2963403868","https://openalex.org/W2964308564","https://openalex.org/W3127686677","https://openalex.org/W4385245566","https://openalex.org/W6639772588","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6688816777","https://openalex.org/W6713752823","https://openalex.org/W6739901393","https://openalex.org/W6789826613"],"related_works":["https://openalex.org/W2275988210","https://openalex.org/W63071447","https://openalex.org/W2385621972","https://openalex.org/W1529400504","https://openalex.org/W2888625260","https://openalex.org/W65617392","https://openalex.org/W2386387936","https://openalex.org/W2589098947","https://openalex.org/W4231964008","https://openalex.org/W2000534859"],"abstract_inverted_index":{"Recent":[0],"voice":[1,92],"activity":[2],"detection":[3,93],"(VAD)":[4],"schemes":[5],"have":[6,39],"aimed":[7],"at":[8,113],"leveraging":[9],"the":[10,20,29,36,44,56,69,83,89,100,114,118,121,126,135],"decent":[11],"neural":[12,46,102],"architectures,":[13],"but":[14],"few":[15],"were":[16],"successful":[17],"with":[18,65,68],"applying":[19],"attention":[21],"network":[22],"due":[23],"to":[24],"its":[25],"high":[26,41],"reliance":[27],"on":[28,43,129],"encoder-decoder":[30],"framework.":[31],"This":[32],"has":[33],"often":[34],"let":[35],"built":[37],"systems":[38],"a":[40,74],"dependency":[42],"recurrent":[45],"networks,":[47],"which":[48],"are":[49],"costly":[50],"and":[51,58,72,77,94,109,138],"sometimes":[52],"less":[53],"context-sensitive":[54],"considering":[55],"scale":[57],"property":[59],"of":[60,106],"acoustic":[61],"frames.":[62],"To":[63],"cope":[64],"this":[66],"issue":[67],"self-attention":[70,84],"mechanism":[71],"achieve":[73],"simple,":[75],"powerful,":[76],"environment-robust":[78],"VAD,":[79],"we":[80],"first":[81],"adopt":[82],"architecture":[85],"in":[86,104],"building":[87],"up":[88],"modules":[90],"for":[91,134],"boosted":[95],"prediction.":[96],"Our":[97],"model":[98],"surpasses":[99],"previous":[101],"architectures":[103],"view":[105],"low":[107],"signal-to-ratio":[108],"noisy":[110],"real-world":[111],"scenarios,":[112],"same":[115],"time":[116],"displaying":[117],"robustness":[119],"regarding":[120],"noise":[122],"types.":[123],"We":[124],"make":[125],"test":[127],"labels":[128],"movie":[130],"data":[131],"publicly":[132],"available":[133],"fair":[136],"competition":[137],"future":[139],"progress.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}