{"id":"https://openalex.org/W3209050974","doi":"https://doi.org/10.1109/taslp.2021.3124420","title":"Robustness of Speech Spoofing Detectors Against Adversarial Post-Processing of Voice Conversion","display_name":"Robustness of Speech Spoofing Detectors Against Adversarial Post-Processing of Voice Conversion","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3209050974","doi":"https://doi.org/10.1109/taslp.2021.3124420","mag":"3209050974"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3124420","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3124420","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5064846647","display_name":"Yiyang Ding","orcid":"https://orcid.org/0009-0008-2518-8392"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi-Yang Ding","raw_affiliation_strings":["University of Science and Technology of China, 12652 Hefei, Anhui, China, (e-mail: dingyiy@mail.ustc.edu.cn)","[National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, 12652 Hefei, Anhui, China, (e-mail: dingyiy@mail.ustc.edu.cn)","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"[National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China]","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026061951","display_name":"Hao-Jian Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao-Jian Lin","raw_affiliation_strings":["University of Science and Technology of China, 12652 Hefei, Anhui, China, (e-mail: linhj@mail.ustc.edu.cn)","[National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, 12652 Hefei, Anhui, China, (e-mail: linhj@mail.ustc.edu.cn)","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"[National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China]","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343789","display_name":"Lijuan Liu","orcid":"https://orcid.org/0009-0007-0163-7336"},"institutions":[{"id":"https://openalex.org/I4210090140","display_name":"IFU (Germany)","ror":"https://ror.org/00ee3x048","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210090140"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Li-Juan Liu","raw_affiliation_strings":["iFLYTEK Co., Ltd, Hefei, Anhui Province, China, 230088 (e-mail: ljliu@iflytek.com)","iFLYTEK Company, Ltd., Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Co., Ltd, Hefei, Anhui Province, China, 230088 (e-mail: ljliu@iflytek.com)","institution_ids":["https://openalex.org/I4210090140"]},{"raw_affiliation_string":"iFLYTEK Company, Ltd., Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["Dept. of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, Anhui, China, 230027 (e-mail: zhling@ustc.edu.cn)","[National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China]"],"raw_orcid":"https://orcid.org/0000-0001-7853-5273","affiliations":[{"raw_affiliation_string":"Dept. of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, Anhui, China, 230027 (e-mail: zhling@ustc.edu.cn)","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"[National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China]","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112134613","display_name":"Yu Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156464","display_name":"Anhui Xinhua University","ror":"https://ror.org/053d7x641","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210156464"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Hu","raw_affiliation_strings":["iFlytek Research, Hefei, Anhui, China, (e-mail: yuhu@iflytek.com)","iFLYTEK Company, Ltd., Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFlytek Research, Hefei, Anhui, China, (e-mail: yuhu@iflytek.com)","institution_ids":["https://openalex.org/I4210156464"]},{"raw_affiliation_string":"iFLYTEK Company, Ltd., Hefei, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2999,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.8407158,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"29","issue":null,"first_page":"3415","last_page":"3426"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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 and Synthesis","score":0.9993000030517578,"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 and Audio Processing","score":0.9872999787330627,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9685999751091003,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8099307417869568},{"id":"https://openalex.org/keywords/spoofing-attack","display_name":"Spoofing attack","score":0.7785382270812988},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7111676931381226},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6748650074005127},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6078388690948486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5036785006523132},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4606819748878479},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.45349299907684326},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4437463879585266},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4423372447490692},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4362648129463196},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.07435339689254761}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8099307417869568},{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.7785382270812988},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7111676931381226},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6748650074005127},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6078388690948486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5036785006523132},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4606819748878479},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.45349299907684326},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4437463879585266},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4423372447490692},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4362648129463196},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.07435339689254761},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2021.3124420","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3124420","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6800000071525574}],"awards":[{"id":"https://openalex.org/G3288249144","display_name":null,"funder_award_id":"2019YFF0303001","funder_id":"https://openalex.org/F4320336026","funder_display_name":"National Key Research and Development Program of China Stem Cell and Translational Research"},{"id":"https://openalex.org/G8663906801","display_name":"\u9762\u5411\u8bed\u97f3\u5408\u6210\u7684\u795e\u7ecf\u7f51\u7edc\u58f0\u7801\u5668\u7814\u7a76","funder_award_id":"61871358","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336026","display_name":"National Key Research and Development Program of China Stem Cell and Translational Research","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1509691205","https://openalex.org/W1673923490","https://openalex.org/W1945616565","https://openalex.org/W2049686551","https://openalex.org/W2086796102","https://openalex.org/W2096555739","https://openalex.org/W2096733369","https://openalex.org/W2107860279","https://openalex.org/W2120605154","https://openalex.org/W2120847449","https://openalex.org/W2123003832","https://openalex.org/W2150769028","https://openalex.org/W2191779130","https://openalex.org/W2295634712","https://openalex.org/W2406312423","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2527729766","https://openalex.org/W2590129515","https://openalex.org/W2608377413","https://openalex.org/W2747024632","https://openalex.org/W2747872086","https://openalex.org/W2799053639","https://openalex.org/W2889329491","https://openalex.org/W2897353073","https://openalex.org/W2936802426","https://openalex.org/W2963138647","https://openalex.org/W2963207607","https://openalex.org/W2963460857","https://openalex.org/W2963466847","https://openalex.org/W2963508548","https://openalex.org/W2964153729","https://openalex.org/W2964301649","https://openalex.org/W2967606780","https://openalex.org/W2972526452","https://openalex.org/W2973252307","https://openalex.org/W2987137416","https://openalex.org/W3015338123","https://openalex.org/W3015811740","https://openalex.org/W3021389849","https://openalex.org/W3026777299","https://openalex.org/W3082130377","https://openalex.org/W3099078140","https://openalex.org/W3099206234","https://openalex.org/W3130210080","https://openalex.org/W3132878323","https://openalex.org/W3198123200","https://openalex.org/W6637162671","https://openalex.org/W6640425456","https://openalex.org/W6687152286","https://openalex.org/W6713727690","https://openalex.org/W6736643613","https://openalex.org/W6761114050","https://openalex.org/W6777494378","https://openalex.org/W6790512957","https://openalex.org/W6791025947","https://openalex.org/W6840412704"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W642007152","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W2401827384","https://openalex.org/W1909292483","https://openalex.org/W1428730622","https://openalex.org/W4294771049","https://openalex.org/W1658560081","https://openalex.org/W596245619"],"abstract_inverted_index":{"With":[0],"the":[1,10,51,67,98,111,119,127,133,138,161,166,173,180,200,207],"development":[2],"of":[3,12,60,69,114,130,143,169,202,209],"speech":[4,15,24,71,99,204],"synthesis":[5],"and":[6,20],"voice":[7,105],"conversion":[8,106],"techniques,":[9],"quality":[11,168],"artificially":[13],"generated":[14],"has":[16],"been":[17],"significantly":[18],"improved":[19],"detecting":[21],"such":[22,30],"spoofing":[23,38,72,211],"becomes":[25],"crucial":[26],"to":[27,158,206],"practical":[28],"applications,":[29],"as":[31,126],"automatic":[32],"speaker":[33],"verification":[34],"(ASV).":[35],"State-of-the-art":[36],"neural-network-based":[37,70],"detection":[39,146,212],"models":[40,122],"can":[41,176],"distinguish":[42],"most":[43],"artificial":[44],"utterances":[45],"from":[46,156],"natural":[47],"ones":[48],"effectively":[49],"in":[50,193],"latest":[52],"ASVspoof":[53],"2019":[54],"evaluation.":[55],"Motivated":[56],"by":[57,96,102,189],"recent":[58],"progresses":[59],"adversarial":[61,75,81,89,112,128,203],"example":[62],"generation,":[63],"this":[64,78],"paper":[65],"studies":[66],"robustness":[68],"detectors":[73,181],"against":[74,91,118,179],"attacks.":[76],"To":[77],"end,":[79],"an":[80],"post-processing":[82,97],"network":[83],"(APN)":[84],"is":[85],"proposed":[86,116],"which":[87,123],"generates":[88],"examples":[90],"a":[92,103,144],"white-box":[93,120,162],"anti-spoofing":[94,121],"model":[95,147],"waveforms":[100],"produced":[101],"baseline":[104],"system.":[107],"Experimental":[108],"results":[109,198],"demonstrate":[110],"ability":[113],"our":[115,194],"APNs":[117,131,175],"were":[124],"used":[125],"targets":[129],"at":[132],"training":[134],"stage.":[135],"For":[136],"example,":[137],"equal":[139],"error":[140],"rate":[141],"(EER)":[142],"fused":[145],"based":[148],"on":[149],"light":[150],"convolution":[151],"neural":[152],"networks":[153],"(LCNNs)":[154],"increased":[155],"0.278%":[157],"12.743%":[159],"under":[160],"condition":[163],"without":[164],"degrading":[165],"subjective":[167],"converted":[170],"speech.":[171],"Furthermore,":[172],"trained":[174],"also":[177],"perform":[178],"with":[182],"either":[183],"unseen":[184,187],"structures":[185],"or":[186],"features":[188],"raising":[190],"their":[191],"EERs":[192],"experiments.":[195],"All":[196],"these":[197],"indicate":[199],"threat":[201],"generation":[205],"performance":[208],"state-of-the-art":[210],"models.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}