{"id":"https://openalex.org/W4307135244","doi":"https://doi.org/10.1186/s13636-022-00260-9","title":"AUC optimization for deep learning-based voice activity detection","display_name":"AUC optimization for deep learning-based voice activity detection","publication_year":2022,"publication_date":"2022-10-22","ids":{"openalex":"https://openalex.org/W4307135244","doi":"https://doi.org/10.1186/s13636-022-00260-9"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-022-00260-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-022-00260-9","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13636-022-00260-9.pdf","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1186/s13636-022-00260-9.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Xiao-Lei Zhang","raw_affiliation_strings":["Research & Development Institute of Northwestern Polytechnical University in Shenzhen, Shenzhen, China","School of Marine Science and Technology, Northwestern Polytechnical University, Xi\u2019an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research & Development Institute of Northwestern Polytechnical University in Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102318256","display_name":"Menglong Xu","orcid":"https://orcid.org/0009-0006-0878-5502"},"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":"Menglong Xu","raw_affiliation_strings":["Research & Development Institute of Northwestern Polytechnical University in Shenzhen, Shenzhen, China","School of Marine Science and Technology, Northwestern Polytechnical University, Xi\u2019an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research & Development Institute of Northwestern Polytechnical University in Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100450091"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":2.3784,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.88971324,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"2022","issue":"1","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":0.9995999932289124,"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":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8207834959030151},{"id":"https://openalex.org/keywords/hinge-loss","display_name":"Hinge loss","score":0.6855098009109497},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5947390794754028},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.58842933177948},{"id":"https://openalex.org/keywords/sigmoid-function","display_name":"Sigmoid function","score":0.5677938461303711},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.5603245496749878},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.518265962600708},{"id":"https://openalex.org/keywords/receiver-operating-characteristic","display_name":"Receiver operating characteristic","score":0.5011875629425049},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4707159399986267},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4499349594116211},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.438664972782135},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36120015382766724},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.25229892134666443},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.17024970054626465},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11714202165603638},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.11063292622566223},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09602570533752441}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8207834959030151},{"id":"https://openalex.org/C39891107","wikidata":"https://www.wikidata.org/wiki/Q5767098","display_name":"Hinge loss","level":3,"score":0.6855098009109497},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5947390794754028},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.58842933177948},{"id":"https://openalex.org/C81388566","wikidata":"https://www.wikidata.org/wiki/Q526668","display_name":"Sigmoid function","level":3,"score":0.5677938461303711},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.5603245496749878},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.518265962600708},{"id":"https://openalex.org/C58471807","wikidata":"https://www.wikidata.org/wiki/Q327120","display_name":"Receiver operating characteristic","level":2,"score":0.5011875629425049},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4707159399986267},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4499349594116211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.438664972782135},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36120015382766724},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25229892134666443},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.17024970054626465},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11714202165603638},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.11063292622566223},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09602570533752441},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-022-00260-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-022-00260-9","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13636-022-00260-9.pdf","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:70094f3c74cd4d9896465b022437f276","is_oa":true,"landing_page_url":"https://doaj.org/article/70094f3c74cd4d9896465b022437f276","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2022, Iss 1, Pp 1-12 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-022-00260-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-022-00260-9","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13636-022-00260-9.pdf","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7900000214576721}],"awards":[{"id":"https://openalex.org/G5057566376","display_name":null,"funder_award_id":"62176211","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4307135244.pdf","grobid_xml":"https://content.openalex.org/works/W4307135244.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1965559434","https://openalex.org/W1972978214","https://openalex.org/W1985242443","https://openalex.org/W1993911116","https://openalex.org/W1999454387","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/W2612770767","https://openalex.org/W2617657420","https://openalex.org/W2889224635","https://openalex.org/W2891182163","https://openalex.org/W2891967288","https://openalex.org/W2939777153","https://openalex.org/W3011405319","https://openalex.org/W3022404557","https://openalex.org/W3160071434","https://openalex.org/W6600001191","https://openalex.org/W6600002382"],"related_works":["https://openalex.org/W4385957115","https://openalex.org/W2061372042","https://openalex.org/W3047779762","https://openalex.org/W2288743358","https://openalex.org/W4281627728","https://openalex.org/W3037097571","https://openalex.org/W4308016144","https://openalex.org/W4307135244","https://openalex.org/W3211032174","https://openalex.org/W3031917044"],"abstract_inverted_index":{"Abstract":[0],"Voice":[1],"activity":[2],"detection":[3],"(VAD)":[4],"based":[5],"on":[6],"deep":[7],"neural":[8,140],"networks":[9],"(DNN)":[10],"have":[11],"demonstrated":[12],"good":[13],"performance":[14,87,188],"in":[15,90,186],"adverse":[16],"acoustic":[17,165,210],"environments.":[18],"Current":[19],"DNN-based":[20],"VAD":[21,39,61,89],"optimizes":[22],"a":[23,34,44,56,137,143],"surrogate":[24],"function,":[25],"e.g.,":[26],"minimum":[27,30,195,199],"cross-entropy":[28],"or":[29,142,159],"squared":[31,196],"error,":[32],"at":[33,62],"given":[35],"decision":[36,46,65],"threshold.":[37],"However,":[38,97],"usually":[40],"works":[41],"on-the-fly":[42],"with":[43,153],"dynamic":[45],"threshold,":[47],"and":[48,122,198,216],"the":[49,74,77,86,93,98,101,112,127,130,150,155,164,182,190,194],"receiver":[50],"operating":[51],"characteristic":[52],"(ROC)":[53],"curve":[54,79],"is":[55,104,204],"global":[57],"evaluation":[58],"metric":[59],"for":[60],"all":[63,172],"possible":[64],"thresholds.":[66],"In":[67],"this":[68,108],"paper,":[69],"we":[70,110,134],"propose":[71],"to":[72,116,171],"maximize":[73,85],"area":[75],"under":[76],"ROC":[78,95],"(MaxAUC)":[80],"by":[81],"DNN,":[82],"which":[83],"can":[84],"of":[88,92,100,129,193],"terms":[91],"entire":[94],"curve.":[96],"objective":[99,184],"AUC":[102,180],"maximization":[103],"nondifferentiable.":[105],"To":[106,125],"overcome":[107],"difficulty,":[109],"relax":[111],"nondifferentiable":[113],"loss":[114,121],"function":[115],"two":[117],"differentiable":[118],"approximation":[119],"functions\u2014sigmoid":[120],"hinge":[123],"loss.":[124],"study":[126],"effectiveness":[128],"proposed":[131],"MaxAUC-DNN":[132],"VAD,":[133],"take":[135],"either":[136,154],"standard":[138],"feedforward":[139],"network":[141,148],"bidirectional":[144],"long":[145],"short-term":[146,160],"memory":[147],"as":[149,163,181],"DNN":[151,208],"model":[152],"state-of-the-art":[156],"multi-resolution":[157],"cochleagram":[158],"Fourier":[161],"transform":[162],"feature.":[166],"We":[167],"conducted":[168],"noise-independent":[169],"training":[170,214],"comparison":[173],"methods.":[174],"Experimental":[175],"results":[176,185],"show":[177],"that":[178],"taking":[179],"optimization":[183],"higher":[187],"than":[189],"common":[191],"objectives":[192],"error":[197],"cross-entropy.":[200],"The":[201],"experimental":[202],"conclusion":[203],"consistent":[205],"across":[206],"different":[207],"structures,":[209],"features,":[211],"noise":[212],"scenarios,":[213],"sets,":[215],"languages.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4}],"updated_date":"2026-06-16T07:32:37.131356","created_date":"2025-10-10T00:00:00"}