{"id":"https://openalex.org/W2294745040","doi":"https://doi.org/10.21437/interspeech.2014-367","title":"Boosted deep neural networks and multi-resolution cochleagram features for voice activity detection","display_name":"Boosted deep neural networks and multi-resolution cochleagram features for voice activity detection","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2294745040","doi":"https://doi.org/10.21437/interspeech.2014-367","mag":"2294745040"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-367","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-367","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","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/A5100450091","display_name":"Xiao-Lei Zhang","orcid":"https://orcid.org/0000-0001-7694-193X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao-Lei Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"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":["Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":60,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9990000128746033,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6956866383552551},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4878966510295868},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4817195534706116},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.47345370054244995},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4537591338157654},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45354193449020386},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.43782398104667664},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33672308921813965}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6956866383552551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4878966510295868},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4817195534706116},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.47345370054244995},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4537591338157654},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45354193449020386},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.43782398104667664},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33672308921813965}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2014-367","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-367","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W1534477342","https://openalex.org/W1985242443","https://openalex.org/W2048497537","https://openalex.org/W2051170812","https://openalex.org/W2062227835","https://openalex.org/W2072219999","https://openalex.org/W2073612610","https://openalex.org/W2075390205","https://openalex.org/W2086723405","https://openalex.org/W2088137865","https://openalex.org/W2098265087","https://openalex.org/W2110622865","https://openalex.org/W2119573952","https://openalex.org/W2123157731","https://openalex.org/W2129120544","https://openalex.org/W2138029428","https://openalex.org/W2142170306","https://openalex.org/W2148632119","https://openalex.org/W2158146178","https://openalex.org/W2168231600","https://openalex.org/W2181395726","https://openalex.org/W2406262283","https://openalex.org/W2561557072"],"related_works":["https://openalex.org/W4375867731","https://openalex.org/W2611989081","https://openalex.org/W2731899572","https://openalex.org/W4304166257","https://openalex.org/W4230611425","https://openalex.org/W4377865163","https://openalex.org/W2799384463","https://openalex.org/W3193857078","https://openalex.org/W3208304128","https://openalex.org/W3000197790"],"abstract_inverted_index":{"Voice":[0],"activity":[1],"detection":[2],"(VAD)":[3],"is":[4],"an":[5],"important":[6],"frontend":[7],"of":[8,55],"many":[9,84],"speech":[10,80],"processing":[11],"systems.":[12],"In":[13],"this":[14],"paper,":[15],"we":[16,59],"describe":[17],"a":[18,38,52,61,101],"new":[19,62],"VAD":[20,92],"algorithm":[21,31],"based":[22],"on":[23],"boosted":[24],"deep":[25],"neural":[26],"networks":[27],"(bDNNs).":[28],"The":[29],"proposed":[30],"first":[32],"generates":[33],"multiple":[34,74],"base":[35,49],"predictions":[36,50],"for":[37,51],"single":[39],"frame":[40],"from":[41],"only":[42],"one":[43],"DNN":[44],"and":[45,77],"then":[46],"aggregates":[47],"the":[48,56,70,94],"better":[53],"prediction":[54],"frame.":[57],"Moreover,":[58],"employ":[60],"acoustic":[63,85],"feature,":[64],"multi-resolution":[65],"cochleagram":[66,71],"(MRCG),":[67],"that":[68,90],"concatenates":[69],"features":[72],"at":[73],"spectrotemporal":[75],"resolutions":[76],"shows":[78],"superior":[79],"separation":[81],"results":[82,88],"over":[83],"features.":[86],"Experimental":[87],"show":[89],"bDNN-based":[91],"with":[93],"MRCG":[95],"feature":[96],"outperforms":[97],"state-of-the-art":[98],"VADs":[99],"by":[100],"considerable":[102],"margin.":[103]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}