{"id":"https://openalex.org/W2988392183","doi":"https://doi.org/10.23919/eusipco.2019.8902703","title":"Context-Aware Neural Voice Activity Detection Using Auxiliary Networks for Phoneme Recognition, Speech Enhancement and Acoustic Scene Classification","display_name":"Context-Aware Neural Voice Activity Detection Using Auxiliary Networks for Phoneme Recognition, Speech Enhancement and Acoustic Scene Classification","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2988392183","doi":"https://doi.org/10.23919/eusipco.2019.8902703","mag":"2988392183"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco.2019.8902703","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2019.8902703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 27th European Signal Processing Conference (EUSIPCO)","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/A5060644399","display_name":"Ryo Masumura","orcid":"https://orcid.org/0000-0002-2415-4149"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Masumura","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078234159","display_name":"Kiyoaki Matsui","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kiyoaki Matsui","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101503856","display_name":"Yuma Koizumi","orcid":"https://orcid.org/0000-0003-3645-6213"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuma Koizumi","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067107593","display_name":"Takaaki Fukutomi","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takaaki Fukutomi","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109336432","display_name":"Takanobu Oba","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takanobu Oba","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067237053","display_name":"Yushi Aono","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yushi Aono","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":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":0.9998000264167786,"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":0.9995999932289124,"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":0.807975172996521},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7951459884643555},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6881074905395508},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6750963926315308},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6465706825256348},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5852201581001282},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4893176257610321},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4854500889778137},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.45759233832359314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4065752625465393},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3752216696739197},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.37494200468063354},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1487564742565155}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.807975172996521},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7951459884643555},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6881074905395508},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6750963926315308},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6465706825256348},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5852201581001282},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4893176257610321},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4854500889778137},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.45759233832359314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4065752625465393},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3752216696739197},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.37494200468063354},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1487564742565155},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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:10.23919/eusipco.2019.8902703","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2019.8902703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 27th European Signal Processing Conference (EUSIPCO)","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":32,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1501987291","https://openalex.org/W1598508708","https://openalex.org/W1985242443","https://openalex.org/W1999454387","https://openalex.org/W2032474878","https://openalex.org/W2035576074","https://openalex.org/W2044893557","https://openalex.org/W2048497537","https://openalex.org/W2059203007","https://openalex.org/W2103636088","https://openalex.org/W2129120544","https://openalex.org/W2147768505","https://openalex.org/W2157825442","https://openalex.org/W2158146178","https://openalex.org/W2160815625","https://openalex.org/W2197404611","https://openalex.org/W2290318471","https://openalex.org/W2296167893","https://openalex.org/W2403004229","https://openalex.org/W2405774341","https://openalex.org/W2407005679","https://openalex.org/W2699195338","https://openalex.org/W2748406667","https://openalex.org/W2775794021","https://openalex.org/W2805233667","https://openalex.org/W2889125325","https://openalex.org/W2913795158","https://openalex.org/W3103619082","https://openalex.org/W6696830301","https://openalex.org/W6713658392","https://openalex.org/W6758876586"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2294333436","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2373767407","https://openalex.org/W2653598178","https://openalex.org/W2747006289","https://openalex.org/W4252682934","https://openalex.org/W2851491717"],"abstract_inverted_index":{"This":[0],"paper":[1,81],"proposes":[2],"a":[3,61,83,100],"novel":[4],"fully":[5],"neural":[6,48,84],"network":[7,64,97,103],"based":[8],"voice":[9],"activity":[10],"detection":[11],"(VAD)":[12],"method":[13,159],"that":[14,55,86,140],"estimates":[15],"whether":[16],"each":[17],"speech":[18,21,39,101,130],"segment":[19],"is":[20,34],"or":[22],"non-speech":[23],"even":[24,119],"in":[25,120,149,160],"very":[26,161],"low":[27,122,162],"signal-to-noise":[28],"ratio":[29],"(SNR)":[30],"environments.":[31,164],"Our":[32],"innovation":[33],"to":[35,116],"improve":[36,66,117],"context-awareness":[37,118],"of":[38,156],"variability":[40],"by":[41],"introducing":[42],"multiple":[43,143],"auxiliary":[44,57,73,88,144],"networks":[45,113],"into":[46],"the":[47,94,154,157],"VAD":[49,67,85,150],"framework.":[50],"While":[51],"previous":[52],"studies":[53],"reported":[54],"phonetic-aware":[56],"features":[58,74,89,145],"extracted":[59,90],"from":[60,91],"phoneme":[62,95],"recognition":[63,96],"can":[65,127],"performance,":[68],"none":[69],"examined":[70],"other":[71],"effective":[72],"for":[75],"enhancing":[76],"noise":[77],"robustness.":[78],"Thus,":[79],"this":[80],"present":[82],"uses":[87],"not":[92],"only":[93],"but":[98],"also":[99],"enhancement":[102],"and":[104,132],"an":[105],"acoustic":[106],"scene":[107],"classification":[108],"network.":[109],"The":[110],"last":[111],"two":[112],"are":[114],"expected":[115],"extremely":[121],"SNR":[123,163],"environments":[124],"since":[125],"they":[126],"extract":[128],"de-noised":[129],"awareness":[131],"noisy":[133],"environment":[134],"awareness.":[135],"In":[136],"addition,":[137],"we":[138],"expect":[139],"combining":[141],"these":[142],"yield":[146],"synergistic":[147],"improvements":[148],"performance.":[151],"Experiments":[152],"verify":[153],"superiority":[155],"proposed":[158]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}