{"id":"https://openalex.org/W3197296485","doi":"https://doi.org/10.1109/tsp52935.2021.9522670","title":"Deep Neural Networks for Voice Activity Detection","display_name":"Deep Neural Networks for Voice Activity Detection","publication_year":2021,"publication_date":"2021-07-26","ids":{"openalex":"https://openalex.org/W3197296485","doi":"https://doi.org/10.1109/tsp52935.2021.9522670","mag":"3197296485"},"language":"en","primary_location":{"id":"doi:10.1109/tsp52935.2021.9522670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp52935.2021.9522670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 44th International Conference on Telecommunications and Signal Processing (TSP)","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/A5020802166","display_name":"\u015eerban Mihalache","orcid":"https://orcid.org/0000-0001-6540-2359"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Serban Mihalache","raw_affiliation_strings":["Speech and Dialogue Research Laboratory, University \u201cPolitehnica\u201d of Bucharest, Romania","Speech and Dialogue Research Laboratory, University \"Politehnica\" of Bucharest, Romania"],"affiliations":[{"raw_affiliation_string":"Speech and Dialogue Research Laboratory, University \u201cPolitehnica\u201d of Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]},{"raw_affiliation_string":"Speech and Dialogue Research Laboratory, University \"Politehnica\" of Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019176282","display_name":"Ioan-Alexandru Ivanov","orcid":null},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Ioan-Alexandru Ivanov","raw_affiliation_strings":["Speech and Dialogue Research Laboratory, University \u201cPolitehnica\u201d of Bucharest, Romania","Speech and Dialogue Research Laboratory, University \"Politehnica\" of Bucharest, Romania"],"affiliations":[{"raw_affiliation_string":"Speech and Dialogue Research Laboratory, University \u201cPolitehnica\u201d of Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]},{"raw_affiliation_string":"Speech and Dialogue Research Laboratory, University \"Politehnica\" of Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012068854","display_name":"Drago\u015f Burileanu","orcid":"https://orcid.org/0000-0002-7675-3506"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Dragos Burileanu","raw_affiliation_strings":["Speech and Dialogue Research Laboratory, University \u201cPolitehnica\u201d of Bucharest, Romania","Speech and Dialogue Research Laboratory, University \"Politehnica\" of Bucharest, Romania"],"affiliations":[{"raw_affiliation_string":"Speech and Dialogue Research Laboratory, University \u201cPolitehnica\u201d of Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]},{"raw_affiliation_string":"Speech and Dialogue Research Laboratory, University \"Politehnica\" of Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020802166"],"corresponding_institution_ids":["https://openalex.org/I61641377"],"apc_list":null,"apc_paid":null,"fwci":0.4571,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.61528059,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"191","last_page":"194"},"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":0.9997000098228455,"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/timit","display_name":"TIMIT","score":0.859954833984375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8272565603256226},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6630502343177795},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.6158299446105957},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5973225831985474},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5623685121536255},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.553613007068634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5192744731903076},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46832090616226196},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4577317535877228},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.440067857503891},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.2392420470714569}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.859954833984375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8272565603256226},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6630502343177795},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.6158299446105957},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5973225831985474},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5623685121536255},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.553613007068634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5192744731903076},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46832090616226196},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4577317535877228},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.440067857503891},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2392420470714569},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsp52935.2021.9522670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp52935.2021.9522670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 44th International Conference on Telecommunications and Signal Processing (TSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7400000095367432,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W315067659","https://openalex.org/W1536583098","https://openalex.org/W1585785493","https://openalex.org/W1597760291","https://openalex.org/W2048497537","https://openalex.org/W2153754015","https://openalex.org/W2160815625","https://openalex.org/W2403700470","https://openalex.org/W2407962166","https://openalex.org/W2509257357","https://openalex.org/W2513345070","https://openalex.org/W2755708162","https://openalex.org/W2891887878","https://openalex.org/W2891967288","https://openalex.org/W3007258144","https://openalex.org/W3127686677","https://openalex.org/W6682824448","https://openalex.org/W6714072840"],"related_works":["https://openalex.org/W2592921646","https://openalex.org/W3156786002","https://openalex.org/W2738221750","https://openalex.org/W2556278835","https://openalex.org/W2732542196","https://openalex.org/W564581980","https://openalex.org/W4295190261","https://openalex.org/W3019117105","https://openalex.org/W2763109982","https://openalex.org/W3175684100"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,99,112],"deep":[6],"neural":[7,37,42],"network":[8],"(DNN)":[9],"system":[10],"for":[11,51,126,132],"the":[12,46,52,84,115,127,133],"automatic":[13],"detection":[14,25],"of":[15,83,114,120],"speech":[16],"in":[17,68],"audio":[18],"signals,":[19],"otherwise":[20],"known":[21],"as":[22,108,110],"voice":[23],"activity":[24],"(VAD).":[26],"Several":[27],"DNN":[28],"types":[29],"were":[30,66,75],"investigated,":[31],"including":[32],"multilayer":[33],"perceptrons":[34],"(MLPs),":[35],"recurrent":[36],"networks":[38,43],"(RNNs),":[39],"and":[40,63,77,93,130],"convolutional":[41],"(CNNs),":[44],"with":[45,87],"best":[47],"performance":[48],"being":[49],"obtained":[50,125],"latter.":[53],"Additional":[54],"postprocessing":[55],"techniques,":[56],"i.e.,":[57],"hysteresis":[58],"thresholds,":[59],"minimum":[60],"duration":[61],"filtering,":[62],"bilateral":[64],"extension,":[65],"employed":[67],"order":[69],"to":[70,122],"boost":[71],"performance.":[72],"The":[73],"systems":[74],"trained":[76],"tested":[78],"using":[79],"several":[80],"data":[81,102],"subsets":[82],"CENSREC-1-C":[85,101,128],"database,":[86],"different":[88,100],"simulated":[89],"ambient":[90,106],"noise":[91],"conditions,":[92],"additional":[94],"testing":[95],"was":[96,124],"done":[97],"on":[98,111],"subset":[103,113],"containing":[104],"actual":[105],"noise,":[107],"well":[109],"TIMIT":[116,134],"database.":[117],"An":[118],"accuracy":[119],"up":[121],"99.13%":[123],"datasets,":[129],"97.60%":[131],"dataset.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
