{"id":"https://openalex.org/W2891182163","doi":"https://doi.org/10.1109/icassp.2018.8461551","title":"Dnn-Based Voice Activity Detection Using Auxiliary Speech Models in Noisy Environments","display_name":"Dnn-Based Voice Activity Detection Using Auxiliary Speech Models in Noisy Environments","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2891182163","doi":"https://doi.org/10.1109/icassp.2018.8461551","mag":"2891182163"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461551","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5022767796","display_name":"Yuuki Tachioka","orcid":"https://orcid.org/0009-0002-0587-2943"},"institutions":[{"id":"https://openalex.org/I4210132650","display_name":"Denso (Japan)","ror":"https://ror.org/04hkpfa76","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210132650"]},{"id":"https://openalex.org/I4210136457","display_name":"Shibuya (Japan)","ror":"https://ror.org/03t1ztz45","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210136457"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuuki Tachioka","raw_affiliation_strings":["Denso IT Laboratory, Shibuya-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Denso IT Laboratory, Shibuya-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I4210132650","https://openalex.org/I4210136457"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5022767796"],"corresponding_institution_ids":["https://openalex.org/I4210132650","https://openalex.org/I4210136457"],"apc_list":null,"apc_paid":null,"fwci":0.6606,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.69409269,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5529","last_page":"5533"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9995999932289124,"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/computer-science","display_name":"Computer science","score":0.7727965116500854},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7568529844284058},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5485442876815796},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5357642769813538},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5324182510375977},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.532218337059021},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5039498209953308},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5013446807861328},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41754698753356934},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.3919847011566162},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37619245052337646},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34469908475875854},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.11735394597053528}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7727965116500854},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7568529844284058},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5485442876815796},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5357642769813538},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5324182510375977},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.532218337059021},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5039498209953308},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5013446807861328},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41754698753356934},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.3919847011566162},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37619245052337646},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34469908475875854},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.11735394597053528},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461551","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":31,"referenced_works":["https://openalex.org/W1571447047","https://openalex.org/W1902027874","https://openalex.org/W1985242443","https://openalex.org/W2009450152","https://openalex.org/W2032474878","https://openalex.org/W2048497537","https://openalex.org/W2059520982","https://openalex.org/W2060417883","https://openalex.org/W2075390205","https://openalex.org/W2091098478","https://openalex.org/W2121973264","https://openalex.org/W2124149378","https://openalex.org/W2129120544","https://openalex.org/W2150769028","https://openalex.org/W2160815625","https://openalex.org/W2184045248","https://openalex.org/W2218015018","https://openalex.org/W2288645994","https://openalex.org/W2395107641","https://openalex.org/W2408688265","https://openalex.org/W2516321201","https://openalex.org/W2642153443","https://openalex.org/W2747798993","https://openalex.org/W3147539069","https://openalex.org/W6646535293","https://openalex.org/W6665887878","https://openalex.org/W6688749188","https://openalex.org/W6696273679","https://openalex.org/W6712351927","https://openalex.org/W6714016741","https://openalex.org/W6739773333"],"related_works":["https://openalex.org/W2919389044","https://openalex.org/W1997528538","https://openalex.org/W2777466939","https://openalex.org/W2889693761","https://openalex.org/W2890579888","https://openalex.org/W1966856063","https://openalex.org/W2593427229","https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2294333436"],"abstract_inverted_index":{"Voice":[0],"activity":[1],"detection":[2],"(VAD)":[3],"is":[4,19,83,92],"essential":[5],"for":[6,53,118],"automatic":[7],"speech":[8,31,79,113],"recognition":[9],"(ASR)":[10],"in":[11,39,106],"noisy":[12,119],"environments.":[13],"Deep":[14],"neural":[15],"network":[16],"(DNN)-based":[17],"VAD":[18,66,120],"more":[20],"powerful":[21],"than":[22,147],"previous":[23],"types.":[24],"In":[25],"the":[26,35,62,90,107,129,142,148],"fields":[27],"of":[28,37,64,73,85,95,128],"ASR":[29,96,111],"and":[30,89,112,134],"enhancement,":[32],"to":[33,41,56,104],"improve":[34,61],"performance":[36,63],"DNNs,":[38],"addition":[40],"spectral":[42],"features,":[43],"auxiliary":[44,74,78,102,137],"features":[45,50,100,138],"are":[46,51],"used":[47],"because":[48],"these":[49],"effective":[52,131],"adapting":[54],"DNNs":[55,105],"a":[57],"target":[58],"environment.":[59],"To":[60],"DNN-based":[65,124],"further,":[67],"this":[68],"paper":[69],"proposes":[70],"two":[71],"types":[72],"feature":[75,144],"based":[76],"on":[77],"models.":[80,98],"The":[81],"first":[82,149],"activation":[84],"non-negative":[86],"matrix":[87],"factorization":[88],"second":[91,143],"acoustic":[93,97],"score":[94],"These":[99],"give":[101],"information":[103],"same":[108],"way":[109],"as":[110],"enhancement":[114],"do.":[115],"Experimental":[116],"results":[117],"tasks":[121],"demonstrated":[122],"that":[123,135],"methods":[125,133],"outperformed":[126],"one":[127],"most":[130],"conventional":[132],"both":[136],"improved":[139],"performance,":[140],"with":[141],"being":[145],"better":[146],"one.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}