{"id":"https://openalex.org/W3010830830","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023262","title":"Voice Activity Detection Based on Time-Delay Neural Networks","display_name":"Voice Activity Detection Based on Time-Delay Neural Networks","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3010830830","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023262","mag":"3010830830"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023262","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023262","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":"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/A5100624455","display_name":"Ye Bai","orcid":"https://orcid.org/0000-0001-5533-6909"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Bai","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, China","School of Artificial Intelligence, University of Chinese Academy of Sciences,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences,China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078525423","display_name":"Jiangyan Yi","orcid":"https://orcid.org/0000-0003-2422-4618"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangyan Yi","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, China","National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["CAS Center for Excellence in Brain Science and Intelligence Technology, Institute of Automation, Chinese Academy of Sciences, China","CAS Center for Excellence in Brain Science and Intelligence Technology, Institute of Automation, Chinese Academy of Sciences,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS Center for Excellence in Brain Science and Intelligence Technology, Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210097554","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"CAS Center for Excellence in Brain Science and Intelligence Technology, Institute of Automation, Chinese Academy of Sciences,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210097554","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111856667","display_name":"Zhengqi Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqi Wen","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, China","National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100395443","display_name":"Bin Liu","orcid":"https://orcid.org/0000-0001-8800-7239"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Liu","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, China","National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"1173","last_page":"1178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9988999962806702,"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":0.9983000159263611,"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":0.6959425806999207},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5225265026092529},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5217538475990295},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.46249130368232727},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3767126798629761},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2727978527545929},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2154410183429718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6959425806999207},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5225265026092529},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5217538475990295},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.46249130368232727},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3767126798629761},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2727978527545929},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2154410183429718}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023262","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023262","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1965559434","https://openalex.org/W1974387177","https://openalex.org/W1985242443","https://openalex.org/W1986103221","https://openalex.org/W2027625247","https://openalex.org/W2032474878","https://openalex.org/W2037227137","https://openalex.org/W2048497537","https://openalex.org/W2059203007","https://openalex.org/W2073693905","https://openalex.org/W2101357962","https://openalex.org/W2103636088","https://openalex.org/W2104132386","https://openalex.org/W2115717467","https://openalex.org/W2117671523","https://openalex.org/W2119573952","https://openalex.org/W2156387975","https://openalex.org/W2157363431","https://openalex.org/W2160815625","https://openalex.org/W2162170885","https://openalex.org/W2165630397","https://openalex.org/W2219249508","https://openalex.org/W2294745040","https://openalex.org/W2396495723","https://openalex.org/W2401364490","https://openalex.org/W2402146185","https://openalex.org/W2406262283","https://openalex.org/W2408468399","https://openalex.org/W2460742184","https://openalex.org/W2519091744","https://openalex.org/W2625979394","https://openalex.org/W2792351646","https://openalex.org/W3145636786","https://openalex.org/W6631362777","https://openalex.org/W6682889407","https://openalex.org/W6683924503","https://openalex.org/W6688816777","https://openalex.org/W6697247452","https://openalex.org/W6712515972","https://openalex.org/W6712930963","https://openalex.org/W6713037448","https://openalex.org/W6713752823"],"related_works":["https://openalex.org/W2386387936","https://openalex.org/W2794438528","https://openalex.org/W2995996972","https://openalex.org/W2312116756","https://openalex.org/W191108438","https://openalex.org/W2368779261","https://openalex.org/W2778699561","https://openalex.org/W3175075966","https://openalex.org/W2893763841","https://openalex.org/W1679636228"],"abstract_inverted_index":{"Voice":[0],"activity":[1],"detection":[2],"(VAD)":[3],"is":[4,15,45,65,85,126],"an":[5,132],"important":[6,16],"preprocessing":[7],"part":[8],"of":[9,55,123],"many":[10],"speech":[11],"applications.":[12],"Context":[13],"information":[14,26],"for":[17],"VAD.":[18],"Time-delay":[19],"neural":[20],"networks":[21],"(TDNNs)":[22],"capture":[23],"long":[24,100],"context":[25],"with":[27,99,140],"a":[28,34,61,109],"few":[29],"parameters.":[30],"This":[31],"paper":[32],"investigates":[33],"TDNN":[35,105],"based":[36,42,106],"VAD":[37],"framework.":[38],"A":[39],"simple":[40],"chunk":[41],"decision":[43,59,129],"method":[44,130,143],"proposed":[46],"to":[47],"smooth":[48],"raw":[49],"posteriors":[50],"and":[51,93,120],"decide":[52],"border":[53],"points":[54],"utterances.":[56],"To":[57],"evaluate":[58],"performance,":[60],"metric":[62],"intersection-over-union":[63],"(IoU)":[64],"introduced":[66],"from":[67],"image":[68],"object":[69],"detection.":[70],"The":[71],"experiment":[72],"results":[73],"are":[74],"evaluated":[75],"on":[76,114,137,144],"Wall":[77],"Street":[78],"Journal":[79],"(WSJ0)":[80],"corpus.":[81],"Frame":[82],"classification":[83],"performance":[84],"measured":[86],"by":[87],"area":[88],"under":[89],"the":[90,104],"curve":[91],"(AUC)":[92],"equal":[94],"error":[95],"rate":[96],"(EER).":[97],"Compared":[98],"short-term":[101],"memory":[102],"baseline,":[103],"system":[107],"achieves":[108,131],"41.26%":[110],"EER":[111],"relative":[112,121,135],"reduction":[113],"average":[115,124,138,142],"in":[116],"matched":[117],"noise":[118],"condition,":[119],"improvement":[122,136],"AUC":[125],"3.82%.":[127],"Proposed":[128],"18.74%":[133],"IoU":[134],"compared":[139],"moving":[141],"average.":[145]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}