{"id":"https://openalex.org/W4387999491","doi":"https://doi.org/10.1145/3630751","title":"Vocoder Detection of Spoofing Speech Based on GAN Fingerprints and Domain Generalization","display_name":"Vocoder Detection of Spoofing Speech Based on GAN Fingerprints and Domain Generalization","publication_year":2023,"publication_date":"2023-10-28","ids":{"openalex":"https://openalex.org/W4387999491","doi":"https://doi.org/10.1145/3630751"},"language":"en","primary_location":{"id":"doi:10.1145/3630751","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3630751","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5100373615","display_name":"Fan Li","orcid":"https://orcid.org/0009-0005-4616-3424"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Li","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0005-4616-3424","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065366225","display_name":"Yanxiang Chen","orcid":"https://orcid.org/0000-0002-1163-7926"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanxiang Chen","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-1163-7926","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100422480","display_name":"Haiyang Liu","orcid":"https://orcid.org/0000-0003-3040-974X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiyang Liu","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-3040-974X","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053462386","display_name":"Zuxing Zhao","orcid":"https://orcid.org/0000-0003-3606-4375"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuxing Zhao","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-3606-4375","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024061393","display_name":"Yuanzhi Yao","orcid":"https://orcid.org/0000-0003-1965-7670"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanzhi Yao","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-1965-7670","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100716299","display_name":"Xin Liao","orcid":"https://orcid.org/0000-0002-9131-0578"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Liao","raw_affiliation_strings":["Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-9131-0578","affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4276,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.84812886,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"20","issue":"6","first_page":"1","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9977999925613403,"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":0.9977999925613403,"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":0.983299970626831,"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":0.9739000201225281,"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":0.8232616782188416},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6714586019515991},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5671772956848145},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5586816072463989},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.483864426612854},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46186643838882446},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4485378563404083},{"id":"https://openalex.org/keywords/fingerprint","display_name":"Fingerprint (computing)","score":0.44060325622558594},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4012411832809448},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11335009336471558}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8232616782188416},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6714586019515991},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5671772956848145},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5586816072463989},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.483864426612854},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46186643838882446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4485378563404083},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.44060325622558594},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4012411832809448},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11335009336471558},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3630751","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3630751","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G3881053923","display_name":null,"funder_award_id":"61972127, 61972142, U22A2030","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7947159105","display_name":"\u89c6\u542c\u89c9\u591a\u5bf9\u9f50\u673a\u5236\u4e0b\u8de8\u6a21\u6001\u751f\u6210\u65b9\u6cd5\u7684\u7814\u7a76","funder_award_id":"61972127","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2519091744","https://openalex.org/W2593768305","https://openalex.org/W2596411757","https://openalex.org/W2602814339","https://openalex.org/W2608207374","https://openalex.org/W2747024632","https://openalex.org/W2747872086","https://openalex.org/W2798658180","https://openalex.org/W2807550049","https://openalex.org/W2811337348","https://openalex.org/W2884585870","https://openalex.org/W2907295878","https://openalex.org/W2952476201","https://openalex.org/W2970006822","https://openalex.org/W2991318208","https://openalex.org/W3015338123","https://openalex.org/W3027857242","https://openalex.org/W3092028330","https://openalex.org/W3104914837","https://openalex.org/W3105402527","https://openalex.org/W3127781933","https://openalex.org/W3158663310","https://openalex.org/W3161236344","https://openalex.org/W3170179936","https://openalex.org/W3204283157","https://openalex.org/W4211148339","https://openalex.org/W4225299853","https://openalex.org/W4292957223","https://openalex.org/W4306317308","https://openalex.org/W4312074759","https://openalex.org/W4360992936","https://openalex.org/W4385800847"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2239445980","https://openalex.org/W2080152487","https://openalex.org/W3083152911","https://openalex.org/W3022347918","https://openalex.org/W4200527723"],"abstract_inverted_index":{"As":[0],"an":[1,42,128],"important":[2],"part":[3],"of":[4,26,37,45,55,67,90,167,222],"the":[5,30,34,64,104,116,141,149,164,168,210,220,223,229,236,240],"text-to-speech":[6],"(TTS)":[7],"system,":[8],"vocoders":[9,19,47,54,204],"convert":[10],"acoustic":[11],"features":[12,152],"into":[13],"speech":[14,28,92,108,111,143,151,195,200],"waveforms.":[15],"The":[16,100,249],"difference":[17],"in":[18,29,63,112,192,228],"is":[20,159,196,205,215,251],"key":[21],"to":[22,60,130,140,147,161,185,208,217],"producing":[23],"different":[24,203,226],"types":[25],"forged":[27,110,142,150,199],"TTS":[31],"system.":[32],"With":[33],"rapid":[35],"development":[36],"general":[38],"adversarial":[39],"networks":[40],"(GANs),":[41],"increasing":[43],"number":[44],"GAN":[46,79,95,132,247],"have":[48],"been":[49],"proposed.":[50],"Detectors":[51],"often":[52],"encounter":[53],"unknown":[56],"types,":[57],"which":[58,193],"leads":[59],"a":[61,123,187],"decline":[62],"generalization":[65,76,158,165,177],"performance":[66],"models.":[68],"However,":[69],"existing":[70],"studies":[71],"lack":[72],"research":[73],"on":[74,78,94,127],"detection":[75,89,117,243],"based":[77,93,126],"vocoders.":[80,135,248],"To":[81],"solve":[82],"this":[83,85],"problem,":[84],"study":[86],"proposes":[87],"vocoder":[88],"spoofed":[91],"fingerprints":[96,133],"and":[97,109,181,198],"domain":[98,157,176],"generalization.":[99],"framework":[101],"can":[102],"widen":[103],"distance":[105],"between":[106],"real":[107,194],"feature":[113,190],"space,":[114],"improving":[115],"model\u2019s":[118],"performance.":[119],"Specifically,":[120],"we":[121],"utilize":[122],"fingerprint":[124],"extractor":[125],"autoencoder":[129],"extract":[131],"from":[134],"We":[136,174],"then":[137],"weight":[138],"them":[139],"for":[144,170],"subsequent":[145],"classification":[146],"learn":[148,186],"with":[153,225],"high":[154],"differentiation.":[155],"Subsequently,":[156],"used":[160,216],"further":[162],"improve":[163],"ability":[166],"model":[169],"unseen":[171],"forgery":[172],"types.":[173],"achieve":[175],"using":[178],"domain-adversarial":[179],"learning":[180,214],"asymmetric":[182],"triplet":[183],"loss":[184],"better":[188],"generalized":[189],"space":[191],"compact":[197],"synthesized":[201],"by":[202],"dispersed.":[206],"Finally,":[207],"optimize":[209],"training":[211,230],"process,":[212],"curriculum":[213],"dynamically":[218],"adjust":[219],"contributions":[221],"samples":[224],"difficulties":[227],"process.":[231],"Experimental":[232],"results":[233,244],"show":[234],"that":[235],"proposed":[237],"method":[238],"achieves":[239],"most":[241],"advanced":[242],"among":[245],"four":[246],"code":[250],"available":[252],"at":[253],"https://github.com/multimedia-infomation-security/GAN-Vocoder-detection":[254],".":[255]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}