{"id":"https://openalex.org/W4405521770","doi":"https://doi.org/10.1109/tifs.2024.3520001","title":"Robust AI-Synthesized Speech Detection Using Feature Decomposition Learning and Synthesizer Feature Augmentation","display_name":"Robust AI-Synthesized Speech Detection Using Feature Decomposition Learning and Synthesizer Feature Augmentation","publication_year":2024,"publication_date":"2024-12-18","ids":{"openalex":"https://openalex.org/W4405521770","doi":"https://doi.org/10.1109/tifs.2024.3520001"},"language":"en","primary_location":{"id":"doi:10.1109/tifs.2024.3520001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2024.3520001","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Forensics and Security","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/A5081311496","display_name":"Kuiyuan Zhang","orcid":"https://orcid.org/0000-0001-6320-9096"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kuiyuan Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-6320-9096","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007080915","display_name":"Zhongyun Hua","orcid":"https://orcid.org/0000-0002-3529-0541"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongyun Hua","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-3529-0541","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085698418","display_name":"Yushu Zhang","orcid":"https://orcid.org/0000-0001-8183-8435"},"institutions":[{"id":"https://openalex.org/I59649739","display_name":"Jiangxi University of Finance and Economics","ror":"https://ror.org/03efmyj29","country_code":"CN","type":"education","lineage":["https://openalex.org/I59649739"]},{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yushu Zhang","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Nanchang, Jiangsu, China","College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0001-8183-8435","affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Nanchang, Jiangsu, China","institution_ids":["https://openalex.org/I59649739"]},{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108575435","display_name":"Yifang Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifang Guo","raw_affiliation_strings":["Alibaba Group, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079461118","display_name":"Tao Xiang","orcid":"https://orcid.org/0000-0002-9439-4623"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Xiang","raw_affiliation_strings":["College of Computer Science, Chongqing University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0002-9439-4623","affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.45,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.90393194,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"20","issue":null,"first_page":"871","last_page":"885"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9714000225067139,"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":0.9714000225067139,"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":0.8290504813194275},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7037370204925537},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6650165915489197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5898875594139099},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5004086494445801},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49048683047294617},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.484321266412735},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.41013872623443604}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8290504813194275},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7037370204925537},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6650165915489197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5898875594139099},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5004086494445801},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49048683047294617},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.484321266412735},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.41013872623443604},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tifs.2024.3520001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2024.3520001","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Forensics and Security","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.41999998688697815,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G2522960279","display_name":null,"funder_award_id":"2024A1515012299","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G5299590918","display_name":null,"funder_award_id":"2022YFB3103500","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7366406415","display_name":null,"funder_award_id":"2024A1515012299","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G8244995127","display_name":"\u9ad8\u7ef4\u9c81\u68d2\u6df7\u6c8c\u673a\u7406\u7814\u7a76\u53ca\u5176\u5728\u751f\u6210\u5f0f\u5bf9\u6297\u7f51\u7edc\u4e2d\u7684\u5e94\u7528","funder_award_id":"62071142","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2606361731","https://openalex.org/W2747024632","https://openalex.org/W2962858109","https://openalex.org/W2963351448","https://openalex.org/W2972359262","https://openalex.org/W2972811785","https://openalex.org/W2982436869","https://openalex.org/W3015338123","https://openalex.org/W3034909238","https://openalex.org/W3096084197","https://openalex.org/W3097777922","https://openalex.org/W3110386488","https://openalex.org/W3170179936","https://openalex.org/W3176445421","https://openalex.org/W3200167423","https://openalex.org/W3201065055","https://openalex.org/W3201506562","https://openalex.org/W3201773091","https://openalex.org/W3209050974","https://openalex.org/W3209984917","https://openalex.org/W4221146610","https://openalex.org/W4224932929","https://openalex.org/W4225420087","https://openalex.org/W4252337780","https://openalex.org/W4284898017","https://openalex.org/W4297841787","https://openalex.org/W4298633873","https://openalex.org/W4308213621","https://openalex.org/W4308477888","https://openalex.org/W4319978495","https://openalex.org/W4367046815","https://openalex.org/W4372346850","https://openalex.org/W4381198892","https://openalex.org/W4382202539","https://openalex.org/W4382202685","https://openalex.org/W4385577110","https://openalex.org/W4385800847","https://openalex.org/W4385823108","https://openalex.org/W4387665604","https://openalex.org/W4392910532","https://openalex.org/W4393156634","https://openalex.org/W4402915903","https://openalex.org/W6745289305","https://openalex.org/W6748409065","https://openalex.org/W6755310813","https://openalex.org/W6767111847","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6795261426","https://openalex.org/W6796464841","https://openalex.org/W6799089041","https://openalex.org/W6849953009","https://openalex.org/W6859999476","https://openalex.org/W6865383027"],"related_works":["https://openalex.org/W2380059383","https://openalex.org/W4224278052","https://openalex.org/W2063679720","https://openalex.org/W3147584709","https://openalex.org/W2031856784","https://openalex.org/W2018218513","https://openalex.org/W2216757598","https://openalex.org/W2185495545","https://openalex.org/W2977677679","https://openalex.org/W2075046161"],"abstract_inverted_index":{"AI-synthesized":[0],"speech,":[1,6],"also":[2],"known":[3],"as":[4,77],"deepfake":[5,34,64,231],"has":[7],"recently":[8],"raised":[9],"significant":[10],"concerns":[11],"due":[12],"to":[13,32,72,140,155,181],"the":[14,92,119,157,161,171,178,196,208,212,219],"rapid":[15],"advancement":[16],"of":[17],"speech":[18,21,51,65,94,139,232],"synthesis":[19],"and":[20,100,143,173,201,205,222,251],"conversion":[22],"techniques.":[23],"Previous":[24],"works":[25],"often":[26],"rely":[27],"on":[28,39,123,229],"distinguishing":[29],"synthesizer":[30,42,98,105,110,116,172,183,189,209],"artifacts":[31,43],"identify":[33],"speech.":[35],"However,":[36],"excessive":[37],"reliance":[38],"these":[40],"specific":[41],"may":[44],"result":[45],"in":[46,108,160],"unsatisfactory":[47],"performance":[48,243],"when":[49],"addressing":[50],"signals":[52],"created":[53],"by":[54,129,169],"unseen":[55],"synthesizers.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60,82,149,185],"propose":[61,83,187],"a":[62,84,97,101,130,188],"robust":[63,241],"detection":[66,242],"method":[67,136],"that":[68,90,193,236],"employs":[69],"feature":[70,86,190,220,225],"decomposition":[71,87],"learn":[73],"synthesizer-independent":[74,125],"content":[75,102,120,126,162,174,213],"features":[76,111,204,210],"complementary":[78],"for":[79,146],"detection.":[80],"Specifically,":[81],"dual-stream":[85],"learning":[88,109,124,133,153],"strategy":[89,192,216],"decomposes":[91],"learned":[93],"representation":[95],"using":[96],"stream":[99,106,121],"stream.":[103,163],"The":[104,164],"specializes":[107],"through":[112],"supervised":[113,132],"training":[114],"with":[115,211],"labels.":[117],"Meanwhile,":[118],"focuses":[122],"features,":[127],"enabled":[128],"pseudo-labeling-based":[131],"method.":[134],"This":[135,215],"randomly":[137,194,206],"transforms":[138],"generate":[141],"speed":[142],"compression":[144],"labels":[145],"training.":[147],"Additionally,":[148],"employ":[150],"an":[151],"adversarial":[152],"technique":[154],"reduce":[156],"synthesizer-related":[158],"components":[159],"final":[165],"classification":[166],"is":[167],"determined":[168],"concatenating":[170],"features.":[175,214],"To":[176],"enhance":[177],"model\u2019s":[179],"robustness":[180],"different":[182],"characteristics,":[184],"further":[186],"augmentation":[191],"blends":[195],"characteristic":[197],"styles":[198],"within":[199],"real":[200],"fake":[202],"audio":[203],"shuffles":[207],"effectively":[217],"enhances":[218],"diversity":[221],"simulates":[223],"more":[224],"combinations.":[226],"Experimental":[227],"results":[228],"four":[230],"benchmark":[233],"datasets":[234],"demonstrate":[235],"our":[237],"model":[238],"achieves":[239],"state-of-the-art":[240],"across":[244],"various":[245],"evaluation":[246],"scenarios,":[247],"including":[248],"cross-method,":[249],"cross-dataset,":[250],"cross-language":[252],"evaluations.":[253]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}