{"id":"https://openalex.org/W4403791366","doi":"https://doi.org/10.1145/3664647.3681100","title":"What's the Real: A Novel Design Philosophy for Robust AI-Synthesized Voice Detection","display_name":"What's the Real: A Novel Design Philosophy for Robust AI-Synthesized Voice Detection","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791366","doi":"https://doi.org/10.1145/3664647.3681100"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681100","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681100","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5075219529","display_name":"Xuan Hai","orcid":"https://orcid.org/0009-0002-0695-2187"},"institutions":[{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Hai","raw_affiliation_strings":["School of Information Science and Engineering, Lanzhou University, Lanzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-0695-2187","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Lanzhou University, Lanzhou, China","institution_ids":["https://openalex.org/I76214153"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352330","display_name":"Xin Liu","orcid":"https://orcid.org/0000-0003-3685-4852"},"institutions":[{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Liu","raw_affiliation_strings":["School of Information Science and Engineering, Lanzhou University, Lanzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3685-4852","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Lanzhou University, Lanzhou, China","institution_ids":["https://openalex.org/I76214153"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101994708","display_name":"Yuan Tan","orcid":"https://orcid.org/0000-0003-3260-6771"},"institutions":[{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Tan","raw_affiliation_strings":["School of Information Science and Engineering, Lanzhou University, Lanzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3260-6771","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Lanzhou University, Lanzhou, China","institution_ids":["https://openalex.org/I76214153"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100682014","display_name":"Gang Liu","orcid":"https://orcid.org/0000-0001-7139-0462"},"institutions":[{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Liu","raw_affiliation_strings":["School of Information Science and Engineering, Lanzhou University, Lanzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7139-0462","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Lanzhou University, Lanzhou, China","institution_ids":["https://openalex.org/I76214153"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100448208","display_name":"Song Li","orcid":"https://orcid.org/0000-0002-7961-8502"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song Li","raw_affiliation_strings":["The State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7961-8502","affiliations":[{"raw_affiliation_string":"The State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029715489","display_name":"Weina Niu","orcid":"https://orcid.org/0000-0002-3235-3463"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weina Niu","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-3235-3463","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114549552","display_name":"Rui Zhou","orcid":"https://orcid.org/0000-0002-9968-6190"},"institutions":[{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhou","raw_affiliation_strings":["School of Information Science and Engineering, Lanzhou University, Lanzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9968-6190","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Lanzhou University, Lanzhou, China","institution_ids":["https://openalex.org/I76214153"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055675863","display_name":"Xiaokang Zhou","orcid":"https://orcid.org/0000-0003-3488-4679"},"institutions":[{"id":"https://openalex.org/I56624758","display_name":"Kansai University","ror":"https://ror.org/03xg1f311","country_code":"JP","type":"education","lineage":["https://openalex.org/I56624758"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xiaokang Zhou","raw_affiliation_strings":["Faculty of Business Data Science, Kansai University, Osaka, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3488-4679","affiliations":[{"raw_affiliation_string":"Faculty of Business Data Science, Kansai University, Osaka, Japan","institution_ids":["https://openalex.org/I56624758"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6900","last_page":"6909"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9986000061035156,"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/T12031","display_name":"Speech and dialogue systems","score":0.9976999759674072,"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":0.6899318695068359},{"id":"https://openalex.org/keywords/philosophy-of-design","display_name":"Philosophy of design","score":0.4900561571121216},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36688852310180664},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.09590551257133484},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.07916620373725891},{"id":"https://openalex.org/keywords/western-philosophy","display_name":"Western philosophy","score":0.07747027277946472}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6899318695068359},{"id":"https://openalex.org/C100694443","wikidata":"https://www.wikidata.org/wiki/Q7186259","display_name":"Philosophy of design","level":3,"score":0.4900561571121216},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36688852310180664},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09590551257133484},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.07916620373725891},{"id":"https://openalex.org/C170143251","wikidata":"https://www.wikidata.org/wiki/Q842333","display_name":"Western philosophy","level":2,"score":0.07747027277946472}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681100","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681100","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1530404542","https://openalex.org/W2394783243","https://openalex.org/W2532494225","https://openalex.org/W2593463961","https://openalex.org/W2807325376","https://openalex.org/W2937579788","https://openalex.org/W2964243274","https://openalex.org/W2972526452","https://openalex.org/W3026777299","https://openalex.org/W3093077017","https://openalex.org/W3110588169","https://openalex.org/W3161782335","https://openalex.org/W3163596559","https://openalex.org/W3174037065","https://openalex.org/W3213029956","https://openalex.org/W4225299853","https://openalex.org/W4385975857","https://openalex.org/W4387969869","https://openalex.org/W4388212422","https://openalex.org/W6960281296"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Voice":[0],"is":[1,195],"one":[2],"of":[3,85,142,163,188],"the":[4,83,97,108,111,115,140,149,154,160,169,176],"most":[5],"widely":[6],"used":[7,74],"media":[8],"for":[9],"information":[10],"transmission":[11],"in":[12,22,75,145,168],"human":[13,103,112,146],"society.":[14],"While":[15],"high-quality":[16],"synthetic":[17,116],"voices":[18,147],"are":[19,181],"extensively":[20],"utilized":[21],"various":[23],"applications,":[24],"they":[25],"pose":[26],"significant":[27],"risks":[28],"to":[29,43,50,67,100,138,152,197,202],"content":[30],"security":[31],"and":[32,71,90,114,148,199],"trust":[33],"building.":[34],"Numerous":[35],"studies":[36],"have":[37],"concentrated":[38],"on":[39,119],"AI-synthesized":[40,126],"voice":[41,61,88,104,113,127,166],"detection":[42,98,128],"mitigate":[44],"these":[45],"risks,":[46],"with":[47],"many":[48],"claiming":[49],"achieve":[51],"promising":[52],"performance.":[53,155],"However,":[54],"recent":[55],"research":[56],"has":[57],"demonstrated":[58],"that":[59,159,193],"fake":[60,87,165],"detectors":[62,89,167],"suffer":[63],"from":[64],"serious":[65],"overfitting":[66],"speaker-irrelative":[68],"features":[69,105],"(SiFs)":[70],"cannot":[72],"be":[73],"real-world":[76],"scenarios.":[77],"In":[78],"this":[79,120],"paper,":[80],"we":[81,122],"analyze":[82],"limitations":[84],"existing":[86,164,203],"propose":[91,123],"a":[92,124],"new":[93],"design":[94],"philosophy,":[95,121],"guiding":[96],"model":[99],"prioritize":[101],"learning":[102,141],"rather":[106],"than":[107,190],"difference":[109],"between":[110],"voice.":[117],"Based":[118],"novel":[125],"framework":[129],"named":[130],"SiFSafer,":[131],"which":[132],"uses":[133],"pre-trained":[134],"speech":[135],"representation":[136],"models":[137],"enhance":[139],"feature":[143],"distribution":[144],"adapter":[150],"fine-tuning":[151],"optimize":[153],"The":[156],"evaluation":[157],"shows":[158],"average":[161],"EERs":[162],"ASVspoof":[170],"datasets":[171],"can":[172],"exceed":[173],"20%":[174],"if":[175],"SiFs":[177,198],"like":[178],"silence":[179],"segments":[180],"removed,":[182],"while":[183],"SiFSafer":[184,194],"achieves":[185],"an":[186],"EER":[187],"less":[189],"8%,":[191],"indicating":[192],"robust":[196],"strongly":[200],"resistant":[201],"attacks.":[204]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
