{"id":"https://openalex.org/W2197404611","doi":"https://doi.org/10.1109/taslp.2015.2505415","title":"Boosting Contextual Information for Deep Neural Network Based Voice Activity Detection","display_name":"Boosting Contextual Information for Deep Neural Network Based Voice Activity Detection","publication_year":2015,"publication_date":"2015-12-04","ids":{"openalex":"https://openalex.org/W2197404611","doi":"https://doi.org/10.1109/taslp.2015.2505415","mag":"2197404611"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2015.2505415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2505415","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":["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/A5100450091","display_name":"Xiao-Lei Zhang","orcid":"https://orcid.org/0000-0001-7694-193X"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao-Lei Zhang","raw_affiliation_strings":["Department of Computer Science & Engineering, The Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Department of Computer Science & Engineering, The Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":11.6538,"has_fulltext":false,"cited_by_count":147,"citation_normalized_percentile":{"value":0.98989662,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"24","issue":"2","first_page":"252","last_page":"264"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.7868423461914062},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6884549260139465},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.577671468257904},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.573276937007904},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5407516956329346},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5401666760444641},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48849594593048096},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4513782262802124},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.41263115406036377},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.4115406274795532}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7868423461914062},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6884549260139465},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.577671468257904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.573276937007904},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5407516956329346},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5401666760444641},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48849594593048096},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4513782262802124},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.41263115406036377},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.4115406274795532},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2015.2505415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2505415","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320313882","display_name":"Medical Research Charities Group","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W1534477342","https://openalex.org/W1536583098","https://openalex.org/W1904365287","https://openalex.org/W1985242443","https://openalex.org/W1988790447","https://openalex.org/W1994387177","https://openalex.org/W1999454387","https://openalex.org/W2015214296","https://openalex.org/W2017608047","https://openalex.org/W2023331723","https://openalex.org/W2023582935","https://openalex.org/W2034300186","https://openalex.org/W2048497537","https://openalex.org/W2072219999","https://openalex.org/W2075390205","https://openalex.org/W2081345242","https://openalex.org/W2088137865","https://openalex.org/W2093717447","https://openalex.org/W2095168618","https://openalex.org/W2095705004","https://openalex.org/W2098265087","https://openalex.org/W2100555417","https://openalex.org/W2101357962","https://openalex.org/W2108819501","https://openalex.org/W2115008841","https://openalex.org/W2121973264","https://openalex.org/W2123157731","https://openalex.org/W2128653836","https://openalex.org/W2129120544","https://openalex.org/W2136922672","https://openalex.org/W2142170306","https://openalex.org/W2147768505","https://openalex.org/W2149053750","https://openalex.org/W2151484683","https://openalex.org/W2158146178","https://openalex.org/W2165563588","https://openalex.org/W2168231600","https://openalex.org/W2168379380","https://openalex.org/W2170644918","https://openalex.org/W2197404611","https://openalex.org/W2294745040","https://openalex.org/W2401364490","https://openalex.org/W2403186097","https://openalex.org/W2406773477","https://openalex.org/W2561557072","https://openalex.org/W2626775259","https://openalex.org/W2887979278","https://openalex.org/W2911964244","https://openalex.org/W2912934387","https://openalex.org/W3004732066","https://openalex.org/W3147539069","https://openalex.org/W4212883601","https://openalex.org/W4248437541","https://openalex.org/W6604254268","https://openalex.org/W6674330103","https://openalex.org/W6682194319","https://openalex.org/W6684859321","https://openalex.org/W6697247452","https://openalex.org/W6713037448","https://openalex.org/W6713746892","https://openalex.org/W6753916174"],"related_works":["https://openalex.org/W2905156999","https://openalex.org/W4229460275","https://openalex.org/W4296079469","https://openalex.org/W1987518466","https://openalex.org/W3135046080","https://openalex.org/W3023033471","https://openalex.org/W2809161969","https://openalex.org/W2964951088","https://openalex.org/W197907117","https://openalex.org/W2280467666"],"abstract_inverted_index":{"Voice":[0],"activity":[1],"detection":[2],"(VAD)":[3],"is":[4,14,53,140],"an":[5,44],"important":[6,15],"topic":[7],"in":[8,61,100],"audio":[9],"signal":[10],"processing.":[11],"Contextual":[12],"information":[13,30,169],"for":[16,131,151],"improving":[17],"the":[18,39,66,69,77,80,92,128,136,156,161,167,172,183,210,223],"performance":[19,217,224],"of":[20,56,68,71,79,117,135,149,200,207],"VAD":[21,185,212],"at":[22,35,175],"low":[23],"signal-to-noise":[24,208],"ratios.":[25],"Here":[26],"we":[27,42,95,159],"explore":[28],"contextual":[29,168],"by":[31,84,121,170,189],"machine":[32],"learning":[33,46],"methods":[34,145],"three":[36],"levels.":[37],"At":[38,91,155],"top":[40],"level,":[41,94,158],"employ":[43,160],"ensemble":[45,57],"framework,":[47],"named":[48,102],"multi-resolution":[49,162],"stacking":[50],"(MRS),":[51],"which":[52,165],"a":[54,62,85,89,97,118,132,190,197,204],"stack":[55],"classifiers.":[58],"Each":[59],"classifier":[60,99],"building":[63,74],"block":[64],"inputs":[65],"concatenation":[67],"predictions":[70,113,130],"its":[72],"lower":[73],"blocks":[75],"and":[76,125,138,203],"expansion":[78],"raw":[81],"acoustic":[82],"feature":[83],"given":[86],"window":[87],"(called":[88],"resolution).":[90],"middle":[93],"describe":[96],"base":[98,112,129,153],"MRS,":[101],"boosted":[103],"deep":[104],"neural":[105],"network":[106],"(bDNN).":[107],"bDNN":[108],"first":[109],"generates":[110],"multiple":[111,152,176],"from":[114,142],"different":[115,141],"contexts":[116],"single":[119],"frame":[120],"only":[122],"one":[123],"DNN":[124],"then":[126],"aggregates":[127],"better":[133],"prediction":[134],"frame,":[137],"it":[139],"computationally-expensive":[143],"boosting":[144],"that":[146,182],"train":[147],"ensembles":[148],"classifiers":[150],"predictions.":[154],"bottom":[157],"cochleagram":[163,173],"feature,":[164],"incorporates":[166],"concatenating":[171],"features":[174],"spectrotemporal":[177],"resolutions.":[178],"Experimental":[179],"results":[180],"show":[181],"MRS-based":[184,211],"outperforms":[186],"other":[187],"VADs":[188],"considerable":[191],"margin.":[192],"Moreover,":[193],"when":[194],"trained":[195],"on":[196,218],"large":[198],"amount":[199],"noise":[201],"types":[202],"wide":[205],"range":[206],"ratios,":[209],"demonstrates":[213],"surprisingly":[214],"good":[215],"generalization":[216],"unseen":[219],"test":[220],"scenarios,":[221],"approaching":[222],"with":[225],"noise-dependent":[226],"training.":[227]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":24},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}