{"id":"https://openalex.org/W2939777153","doi":"https://doi.org/10.1109/icassp.2019.8682803","title":"AUC Optimization for Deep Learning Based Voice Activity Detection","display_name":"AUC Optimization for Deep Learning Based Voice Activity Detection","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2939777153","doi":"https://doi.org/10.1109/icassp.2019.8682803","mag":"2939777153"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682803","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5102759368","display_name":"Zi-Chen Fan","orcid":"https://orcid.org/0009-0009-7355-8594"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zi-Chen Fan","raw_affiliation_strings":["Center for Intelligent Acoustics and Immersive Communications and School of Marine Science and Technology, Northwestern Polytechnical University"],"affiliations":[{"raw_affiliation_string":"Center for Intelligent Acoustics and Immersive Communications and School of Marine Science and Technology, Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041350492","display_name":"Zhongxin Bai","orcid":"https://orcid.org/0000-0003-3575-7014"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongxin Bai","raw_affiliation_strings":["Center for Intelligent Acoustics and Immersive Communications and School of Marine Science and Technology, Northwestern Polytechnical University"],"affiliations":[{"raw_affiliation_string":"Center for Intelligent Acoustics and Immersive Communications and School of Marine Science and Technology, Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450091","display_name":"Xiao-Lei Zhang","orcid":"https://orcid.org/0000-0001-7694-193X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Lei Zhang","raw_affiliation_strings":["Center for Intelligent Acoustics and Immersive Communications and School of Marine Science and Technology, Northwestern Polytechnical University"],"affiliations":[{"raw_affiliation_string":"Center for Intelligent Acoustics and Immersive Communications and School of Marine Science and Technology, Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054558832","display_name":"Susanto Rahardja","orcid":"https://orcid.org/0000-0003-0831-6934"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Susanto Rahardja","raw_affiliation_strings":["Center for Intelligent Acoustics and Immersive Communications and School of Marine Science and Technology, Northwestern Polytechnical University"],"affiliations":[{"raw_affiliation_string":"Center for Intelligent Acoustics and Immersive Communications and School of Marine Science and Technology, Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056129529","display_name":"Jingdong Chen","orcid":"https://orcid.org/0000-0003-0083-9247"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingdong Chen","raw_affiliation_strings":["Center for Intelligent Acoustics and Immersive Communications and School of Marine Science and Technology, Northwestern Polytechnical University"],"affiliations":[{"raw_affiliation_string":"Center for Intelligent Acoustics and Immersive Communications and School of Marine Science and Technology, Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102759368"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":3.5051,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.93567429,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"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/T11309","display_name":"Music 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":0.9983000159263611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6843037605285645},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6131537556648254},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5965008735656738},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.5582096576690674},{"id":"https://openalex.org/keywords/receiver-operating-characteristic","display_name":"Receiver operating characteristic","score":0.5265672206878662},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5112688541412354},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5030643343925476},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.49592217803001404},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.49457356333732605},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.44409409165382385},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4428369700908661},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.43977367877960205},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4239670932292938},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4233807325363159},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34963661432266235},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.18546032905578613},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.155499666929245},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1361495554447174},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09358006715774536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6843037605285645},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6131537556648254},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5965008735656738},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.5582096576690674},{"id":"https://openalex.org/C58471807","wikidata":"https://www.wikidata.org/wiki/Q327120","display_name":"Receiver operating characteristic","level":2,"score":0.5265672206878662},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5112688541412354},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5030643343925476},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.49592217803001404},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.49457356333732605},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.44409409165382385},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4428369700908661},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.43977367877960205},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4239670932292938},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4233807325363159},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34963661432266235},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.18546032905578613},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.155499666929245},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1361495554447174},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09358006715774536},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682803","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.800000011920929,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W8545729","https://openalex.org/W1965559434","https://openalex.org/W1985242443","https://openalex.org/W1993911116","https://openalex.org/W1999454387","https://openalex.org/W2017608047","https://openalex.org/W2048497537","https://openalex.org/W2065238411","https://openalex.org/W2075390205","https://openalex.org/W2098265087","https://openalex.org/W2108819501","https://openalex.org/W2109000787","https://openalex.org/W2129120544","https://openalex.org/W2145524159","https://openalex.org/W2145887942","https://openalex.org/W2162520685","https://openalex.org/W2170644918","https://openalex.org/W2171875099","https://openalex.org/W2194940824","https://openalex.org/W2197404611","https://openalex.org/W2396495723","https://openalex.org/W2617657420","https://openalex.org/W2753897885","https://openalex.org/W2788770315","https://openalex.org/W2889224635","https://openalex.org/W2891182163","https://openalex.org/W2891967288","https://openalex.org/W3145636786","https://openalex.org/W6600359219","https://openalex.org/W6712515972"],"related_works":["https://openalex.org/W2803187616","https://openalex.org/W2963759070","https://openalex.org/W2364132456","https://openalex.org/W2378228316","https://openalex.org/W2895864717","https://openalex.org/W2972417230","https://openalex.org/W2951244744","https://openalex.org/W2944701285","https://openalex.org/W2378137772","https://openalex.org/W4372054758"],"abstract_inverted_index":{"Voice":[0],"activity":[1],"detection":[2],"(VAD)":[3],"based":[4,20],"on":[5],"deep":[6],"neural":[7],"networks":[8],"(DNN)":[9],"has":[10],"demonstrated":[11],"good":[12],"performance":[13,61,88,108],"in":[14,91,106],"adverse":[15],"acoustic":[16],"environments.":[17],"Current":[18],"DNN":[19,104],"VAD":[21,39,57,63,90],"optimizes":[22],"a":[23,34,44,52],"surrogate":[24],"function,":[25],"e.g.":[26],"minimum":[27,30,116],"cross-entropy":[28],"or":[29],"squared":[31,117],"error,":[32],"at":[33,64],"given":[35],"decision":[36,46,67],"threshold.":[37],"However,":[38],"usually":[40],"works":[41],"on-the-fly":[42],"with":[43],"dynamic":[45],"threshold;":[47],"and":[48],"ROC":[49,79,95],"curve":[50,80],"is":[51],"global":[53],"evaluation":[54],"metric":[55],"of":[56,62,89,93,113],"that":[58,100],"reflects":[59],"the":[60,76,87,94,110,115],"all":[65],"possible":[66],"thresholds.":[68],"In":[69],"this":[70],"paper,":[71],"we":[72],"propose":[73],"to":[74],"optimize":[75],"area":[77],"under":[78],"(AUC)":[81],"by":[82,103,119],"DNN,":[83],"which":[84],"can":[85],"maximize":[86],"terms":[92],"curve.":[96],"Experimental":[97],"results":[98,105],"show":[99],"optimizing":[101,114],"AUC":[102],"higher":[107],"than":[109],"common":[111],"method":[112],"error":[118],"DNN.":[120]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}