{"id":"https://openalex.org/W4390691474","doi":"https://doi.org/10.1109/tifs.2024.3352429","title":"One-Class Neural Network With Directed Statistics Pooling for Spoofing Speech Detection","display_name":"One-Class Neural Network With Directed Statistics Pooling for Spoofing Speech Detection","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4390691474","doi":"https://doi.org/10.1109/tifs.2024.3352429"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2024.3352429","pdf_url":null,"source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-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/A5012544249","display_name":"Guoyuan Lin","orcid":"https://orcid.org/0000-0003-1293-0718"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoyuan Lin","raw_affiliation_strings":["Guangdong Province Key Laboratory of Information Security Technology and the School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Guangdong Province Key Laboratory of Information Security Technology and the School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102785655","display_name":"Weiqi Luo","orcid":"https://orcid.org/0000-0002-8999-6064"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiqi Luo","raw_affiliation_strings":["Guangdong Province Key Laboratory of Information Security Technology and the School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Guangdong Province Key Laboratory of Information Security Technology and the School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016625595","display_name":"Da Luo","orcid":"https://orcid.org/0000-0002-4816-1677"},"institutions":[{"id":"https://openalex.org/I2799850029","display_name":"Dongguan University of Technology","ror":"https://ror.org/01m8p7q42","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799850029"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Da Luo","raw_affiliation_strings":["School of Computer Science and Technology, Dongguan University of Technology, Dongguan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dongguan University of Technology, Dongguan, China","institution_ids":["https://openalex.org/I2799850029"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047964483","display_name":"Jiwu Huang","orcid":"https://orcid.org/0000-0002-7625-5689"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiwu Huang","raw_affiliation_strings":["Guangdong Key Laboratory of Intelligent Information Processing and the Shenzhen Key Laboratory of Media Security, Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Guangdong Key Laboratory of Intelligent Information Processing and the Shenzhen Key Laboratory of Media Security, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.116,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.999975,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"19","issue":null,"first_page":"2581","last_page":"2593"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition Technology","score":0.9993,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition Technology","score":0.9993,"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/T10860","display_name":"Speech Enhancement Techniques","score":0.9975,"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/T10863","display_name":"Diagnosis and Treatment of Voice Disorders","score":0.9828,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.7913519},{"id":"https://openalex.org/keywords/spoofing-attack","display_name":"Spoofing attack","score":0.71146023},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.6991533},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.59698534},{"id":"https://openalex.org/keywords/end-to-end-speech-recognition","display_name":"End-to-End Speech Recognition","score":0.55133},{"id":"https://openalex.org/keywords/audio-visual-speech-recognition","display_name":"Audio-Visual Speech Recognition","score":0.541585},{"id":"https://openalex.org/keywords/statistical-language-modeling","display_name":"Statistical Language Modeling","score":0.538156},{"id":"https://openalex.org/keywords/acoustic-modeling","display_name":"Acoustic Modeling","score":0.536451},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep Learning","score":0.53022},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47677782},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.44777486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.85479957},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.7913519},{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.71146023},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6991533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6378663},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.59698534},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4984665},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47677782},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44991562},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.44777486},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44486904},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41705585},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2024.3352429","pdf_url":null,"source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, justice, and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.63}],"grants":[{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":"U19B2022"},{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":"61972430"}],"datasets":[],"versions":[],"referenced_works_count":47,"referenced_works":["https://openalex.org/W2014485509","https://openalex.org/W2123299109","https://openalex.org/W2143597468","https://openalex.org/W2154278880","https://openalex.org/W2176804518","https://openalex.org/W2295634712","https://openalex.org/W2303197844","https://openalex.org/W2407170210","https://openalex.org/W2464759814","https://openalex.org/W2532494225","https://openalex.org/W2598638573","https://openalex.org/W2745896134","https://openalex.org/W2960139675","https://openalex.org/W2962761264","https://openalex.org/W2963138647","https://openalex.org/W2963508548","https://openalex.org/W2964052309","https://openalex.org/W2964301388","https://openalex.org/W2967606780","https://openalex.org/W2972594541","https://openalex.org/W2972786657","https://openalex.org/W2972811785","https://openalex.org/W2972909277","https://openalex.org/W2973164265","https://openalex.org/W2973181078","https://openalex.org/W3049278490","https://openalex.org/W3081168214","https://openalex.org/W3096084197","https://openalex.org/W3132550238","https://openalex.org/W3133379831","https://openalex.org/W3158663310","https://openalex.org/W3161011913","https://openalex.org/W3163596559","https://openalex.org/W3170179936","https://openalex.org/W3197134965","https://openalex.org/W3197358873","https://openalex.org/W3198486673","https://openalex.org/W3200167423","https://openalex.org/W3201197228","https://openalex.org/W3201773091","https://openalex.org/W4285149944","https://openalex.org/W4312702685","https://openalex.org/W4323022270","https://openalex.org/W4360992936","https://openalex.org/W4366352743","https://openalex.org/W4372184039","https://openalex.org/W4375869011"],"related_works":["https://openalex.org/W4318954401","https://openalex.org/W4298017035","https://openalex.org/W4226354336","https://openalex.org/W3128220493","https://openalex.org/W3110700750","https://openalex.org/W3026913501","https://openalex.org/W2998675825","https://openalex.org/W2897443685","https://openalex.org/W2792147139","https://openalex.org/W2736804899"],"abstract_inverted_index":{"Existing":[0],"deep":[1],"learning":[2,38],"models":[3],"for":[4,99,156],"spoofing":[5,15,104,124],"speech":[6,85,170],"detection":[7,151],"often":[8],"struggle":[9],"to":[10,13,70,196],"effectively":[11],"generalize":[12],"unseen":[14],"attacks":[16],"that":[17,94,132],"were":[18],"not":[19],"present":[20,49],"during":[21,126],"the":[22,26,37,75,81,109,120,133,157,164,198,203],"training":[23],"stage.":[24],"Moreover,":[25,163],"presence":[27],"of":[28,77,84,123,146,154,172,202],"class":[29,116],"imbalance":[30,117],"further":[31],"compounds":[32],"this":[33],"issue":[34],"by":[35,118],"biasing":[36],"process":[39],"towards":[40],"seen":[41],"attack":[42],"samples.":[43],"To":[44],"address":[45],"these":[46],"challenges,":[47],"we":[48,87],"an":[50,142],"innovative":[51],"end-to-end":[52],"model":[53,64,135],"called":[54],"One-Class":[55],"Neural":[56],"Network":[57],"with":[58,190],"Directed":[59],"Statistics":[60],"Pooling":[61],"(OCNet-DSP).":[62],"Our":[63],"incorporates":[65],"a":[66,89,149,191],"feature":[67],"cropping":[68],"operation":[69],"attenuate":[71],"high-frequency":[72],"components,":[73],"mitigating":[74],"risk":[76],"overfitting.":[78],"Additionally,":[79,185],"leveraging":[80],"time-frequency":[82],"characteristics":[83],"signals,":[86],"introduce":[88],"directed":[90],"statistics":[91],"pooling":[92],"layer":[93],"extracts":[95],"more":[96],"effective":[97],"features":[98],"distinguishing":[100],"between":[101],"bonafide":[102],"and":[103,148,200],"classes.":[105],"We":[106],"also":[107],"propose":[108],"Threshold":[110],"One-class":[111],"Softmax":[112],"loss,":[113],"which":[114,168],"mitigates":[115],"reducing":[119],"optimization":[121],"weight":[122],"samples":[125],"training.":[127],"Extensive":[128],"comparative":[129],"results":[130],"demonstrate":[131],"proposed":[134,165,204],"outperforms":[136],"all":[137],"existing":[138],"single":[139],"models,":[140],"achieving":[141],"equal":[143],"error":[144],"rate":[145],"0.44%":[147],"minimum":[150],"cost":[152],"function":[153],"0.0145":[155],"ASVspoof":[158],"2019":[159],"logical":[160],"access":[161],"database.":[162],"ensemble":[166,183],"version,":[167],"accommodates":[169],"inputs":[171],"varying":[173],"lengths":[174],"in":[175],"each":[176],"submodel,":[177],"maintains":[178],"state-of-the-art":[179],"performance":[180],"among":[181],"reproducible":[182],"models.":[184],"numerous":[186],"ablation":[187],"experiments,":[188],"along":[189],"cross-dataset":[192],"experiment,":[193],"are":[194],"conducted":[195],"validate":[197],"rationality":[199],"effectiveness":[201],"model.":[205]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4390691474","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2024-12-01T19:17:09.890084","created_date":"2024-01-13"}