{"id":"https://openalex.org/W3010659501","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023320","title":"An RNN and CRNN Based Approach to Robust Voice Activity Detection","display_name":"An RNN and CRNN Based Approach to Robust Voice Activity Detection","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3010659501","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023320","mag":"3010659501"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5046540992","display_name":"Guan-Bo Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guan-Bo Wang","raw_affiliation_strings":["Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100692904","display_name":"Wei-Qiang Zhang","orcid":"https://orcid.org/0000-0003-3841-1959"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Qiang Zhang","raw_affiliation_strings":["Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5046540992"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.9951,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.77617528,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1347","last_page":"1350"},"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":0.9998000264167786,"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":0.9993000030517578,"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":0.8168161511421204},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.781674861907959},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6253668069839478},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5826276540756226},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5558866262435913},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.49206894636154175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40538713335990906},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.31557777523994446},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.24519002437591553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8168161511421204},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.781674861907959},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6253668069839478},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5826276540756226},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5558866262435913},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.49206894636154175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40538713335990906},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31557777523994446},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.24519002437591553}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6700000166893005,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W1985242443","https://openalex.org/W2044893557","https://openalex.org/W2103635001","https://openalex.org/W2806318065","https://openalex.org/W2810313973","https://openalex.org/W2917987043","https://openalex.org/W2928746352","https://openalex.org/W2972922917","https://openalex.org/W4254642886","https://openalex.org/W6752435643"],"related_works":["https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2131711534","https://openalex.org/W2559837139","https://openalex.org/W1151175420","https://openalex.org/W2407342067","https://openalex.org/W2166690696","https://openalex.org/W2541680182"],"abstract_inverted_index":{"In":[0,25],"this":[1],"paper,":[2],"we":[3,39],"propose":[4],"a":[5,13,20,42,45,50],"voice":[6],"activity":[7],"detection":[8],"(VAD)":[9],"system,":[10,91],"which":[11,56],"combines":[12],"convolutional":[14],"recurrent":[15,21],"neural":[16,22],"network":[17,23],"(CRNN)":[18],"and":[19,49,72],"(RNN).":[24],"order":[26],"to":[27,88],"improve":[28],"the":[29,89],"performance":[30],"of":[31,55,67],"our":[32,61,92],"system":[33,63,94],"in":[34],"low":[35],"signal-noise":[36],"ratio":[37],"conditions,":[38],"also":[40],"add":[41],"speech-enhancement":[43],"module,":[44,48,53],"one-dimensional":[46],"dilation-erosion":[47],"model":[51],"ensemble":[52],"all":[54],"contribute":[57],"significantly.":[58],"We":[59],"evaluate":[60],"proposed":[62,93],"on":[64],"development":[65],"dataset":[66],"Public":[68],"Safety":[69],"Communications":[70],"(PSC)":[71],"Video":[73],"Annotation":[74],"for":[75],"Speech":[76,82],"Technologies":[77,84],"(VAST)":[78],"from":[79],"NIST":[80],"Open":[81],"Analytic":[83],"2019":[85],"(OpenSAT19).":[86],"Compared":[87],"baseline":[90],"achieves":[95],"better":[96],"performance,":[97],"using":[98],"OpenSAT19":[99],"official":[100],"evaluation":[101],"metrics.":[102]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}