{"id":"https://openalex.org/W4385521743","doi":"https://doi.org/10.1109/access.2023.3301616","title":"Contributions of Jitter and Shimmer in the Voice for Fake Audio Detection","display_name":"Contributions of Jitter and Shimmer in the Voice for Fake Audio Detection","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385521743","doi":"https://doi.org/10.1109/access.2023.3301616"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3301616","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3301616","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10207023.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10207023.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100763790","display_name":"Li Kai","orcid":"https://orcid.org/0000-0002-6633-3954"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kai Li","raw_affiliation_strings":["Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034792613","display_name":"Xugang Lu","orcid":"https://orcid.org/0000-0001-7075-448X"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xugang Lu","raw_affiliation_strings":["Advanced Speech Technology Laboratory, National Institute of Information and Communications Technology, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Advanced Speech Technology Laboratory, National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055059119","display_name":"Masato Akagi","orcid":"https://orcid.org/0000-0003-2450-6754"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Akagi","raw_affiliation_strings":["Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014199725","display_name":"Masashi Unoki","orcid":"https://orcid.org/0000-0002-6605-2052"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masashi Unoki","raw_affiliation_strings":["Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100763790"],"corresponding_institution_ids":["https://openalex.org/I177738480"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":3.7281,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.94434481,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"11","issue":null,"first_page":"84689","last_page":"84698"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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/jitter","display_name":"Jitter","score":0.7541033029556274},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.7265681028366089},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7076994776725769},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6998788118362427},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6239970922470093},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5144705772399902},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47462546825408936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4735740125179291},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42314398288726807},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.382731556892395},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08401688933372498}],"concepts":[{"id":"https://openalex.org/C134652429","wikidata":"https://www.wikidata.org/wiki/Q1052698","display_name":"Jitter","level":2,"score":0.7541033029556274},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7265681028366089},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7076994776725769},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6998788118362427},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6239970922470093},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5144705772399902},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47462546825408936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4735740125179291},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42314398288726807},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.382731556892395},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08401688933372498},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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":2,"locations":[{"id":"doi:10.1109/access.2023.3301616","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3301616","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10207023.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:5fbbd8ddd4724a6b93b544bfe2ffd3ca","is_oa":true,"landing_page_url":"https://doaj.org/article/5fbbd8ddd4724a6b93b544bfe2ffd3ca","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 84689-84698 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3301616","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3301616","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10207023.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G190845862","display_name":null,"funder_award_id":"201605002","funder_id":"https://openalex.org/F4320325628","funder_display_name":"Ministry of Internal Affairs and Communications"},{"id":"https://openalex.org/G2732612706","display_name":null,"funder_award_id":"SCOPE","funder_id":"https://openalex.org/F4320325628","funder_display_name":"Ministry of Internal Affairs and Communications"}],"funders":[{"id":"https://openalex.org/F4320325628","display_name":"Ministry of Internal Affairs and Communications","ror":"https://ror.org/00vs1pz50"},{"id":"https://openalex.org/F4320327368","display_name":"KDDI Foundation","ror":null},{"id":"https://openalex.org/F4320335839","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385521743.pdf","grobid_xml":"https://content.openalex.org/works/W4385521743.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W36638734","https://openalex.org/W1544215838","https://openalex.org/W1972438889","https://openalex.org/W1975079546","https://openalex.org/W2058650262","https://openalex.org/W2091425152","https://openalex.org/W2118774185","https://openalex.org/W2126829180","https://openalex.org/W2148154194","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2298367083","https://openalex.org/W2316846205","https://openalex.org/W2576309025","https://openalex.org/W2590129515","https://openalex.org/W2747024632","https://openalex.org/W2752782242","https://openalex.org/W2791616807","https://openalex.org/W2795109282","https://openalex.org/W2807550049","https://openalex.org/W2936802426","https://openalex.org/W2946200149","https://openalex.org/W2963460857","https://openalex.org/W2967606780","https://openalex.org/W2972526452","https://openalex.org/W2972786657","https://openalex.org/W2973181078","https://openalex.org/W2996395154","https://openalex.org/W2999174651","https://openalex.org/W3033411150","https://openalex.org/W3036601975","https://openalex.org/W3096333737","https://openalex.org/W3097073051","https://openalex.org/W3098557217","https://openalex.org/W3128666957","https://openalex.org/W3131470072","https://openalex.org/W3131786367","https://openalex.org/W3160325739","https://openalex.org/W3197358873","https://openalex.org/W3197934651","https://openalex.org/W3198329097","https://openalex.org/W3203313352","https://openalex.org/W3212117663","https://openalex.org/W4221138880","https://openalex.org/W4295312788","https://openalex.org/W4295731579","https://openalex.org/W4297841233","https://openalex.org/W4312096005","https://openalex.org/W4378506723","https://openalex.org/W6601463856","https://openalex.org/W6638444622","https://openalex.org/W6678701371","https://openalex.org/W6763832098","https://openalex.org/W6766978945","https://openalex.org/W6778823374","https://openalex.org/W6780218876","https://openalex.org/W6791380813","https://openalex.org/W6801032166","https://openalex.org/W6803757597","https://openalex.org/W6852755086"],"related_works":["https://openalex.org/W169399214","https://openalex.org/W3100825170","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W2108985546","https://openalex.org/W2433276473","https://openalex.org/W3149582125","https://openalex.org/W2077992636"],"abstract_inverted_index":{"Fake":[0],"audio":[1],"detection":[2,69],"(FAD)":[3],"aims":[4],"to":[5,36,242,260],"identify":[6],"fraudulent":[7],"speech":[8,29,59,86],"generated":[9],"through":[10],"advanced":[11],"speech-synthesis":[12],"techniques.":[13],"Most":[14],"current":[15],"FAD":[16,200,246],"methods":[17],"rely":[18],"solely":[19],"on":[20,121],"a":[21,127,182,268],"deep":[22],"neural":[23],"network":[24],"(DNN)":[25],"framework":[26],"with":[27,232],"either":[28],"waveforms":[30],"or":[31],"commonly":[32],"used":[33],"acoustic":[34],"features":[35],"extract":[37],"high-level":[38],"representations,":[39,151],"overlooking":[40],"the":[41,56,68,77,89,95,109,122,171,175,188,196,204,222,233,243,253,264],"analysis":[42],"of":[43,58,70,97,111,138,170,195,206,271],"prosody":[44,80],"differences":[45,78,106],"between":[46,82,115],"genuine":[47,83],"and":[48,60,84,91,113,117,148,166,190,213,224,235],"fake":[49,71,85,116,132],"speech.":[50,133],"Prosody":[51],"carries":[52],"important":[53],"cues":[54],"about":[55],"naturalness":[57],"emotional":[61],"content,":[62],"which":[63],"can":[64,238],"be":[65],"leveraged":[66],"in":[67,79,108,168,174,203,263],"audio.":[72],"This":[73],"paper":[74],"explicitly":[75,186],"investigates":[76],"information":[81],"represented":[87],"by":[88,185],"jitter":[90,112,147],"shimmer":[92,114,123,149,189,227],"features.":[93,192],"On":[94],"basis":[96],"our":[98],"investigation,":[99],"we":[100,152,180],"found":[101],"strong":[102],"evidence":[103],"that":[104,125,220,230],"obvious":[105],"exist":[107],"level":[110],"real":[118],"speech,":[119],"particularly":[120],"feature":[124,150,176],"has":[126],"large":[128],"dynamic":[129,225],"variation":[130],"for":[131,145,199],"To":[134],"ensure":[135],"accurate":[136],"estimation":[137,163],"<italic":[139,157],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[140,143,158,161],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">F</i>":[141,159],"<sub":[142,160],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">0</sub>":[144,162],"better":[146],"propose":[153],"using":[154],"two":[155],"additional":[156],"methods,":[164],"YIN":[165,234],"SWIPE,":[167],"place":[169],"IRAPT":[172],"algorithm":[173],"extraction":[177],"process.":[178],"Moreover,":[179],"design":[181],"DNN-FAD":[183],"system":[184],"combining":[187],"Mel-spectrogram":[191],"The":[193,216,248],"effectiveness":[194],"proposed":[197],"method":[198],"is":[201],"evaluated":[202],"datasets":[205],"Audio":[207],"Deep":[208],"Synthesis":[209],"Detection":[210],"(ADD)":[211],"2022":[212],"2023":[214],"challenges.":[215],"experimental":[217],"results":[218,250],"show":[219],"both":[221],"static":[223],"continuous":[226],"features,":[228],"especially":[229],"extracted":[231],"SWIPE":[236],"algorithms,":[237],"provide":[239],"complementary":[240],"knowledge":[241],"traditional":[244],"spectrum-based":[245],"systems.":[247],"optimal":[249],"effectively":[251],"reduce":[252],"equal":[254],"error":[255],"rate":[256],"from":[257],"41.29":[258],"%":[259,262],"35.77":[261],"ADD2023":[265],"challenge,":[266],"achieving":[267],"relative":[269],"improvement":[270],"13.37":[272],"%.":[273]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}