{"id":"https://openalex.org/W4403165616","doi":"https://doi.org/10.1587/transinf.2024mui0001","title":"Deepfake Speech Detection: Approaches from Acoustic Features to Deep Neural Networks","display_name":"Deepfake Speech Detection: Approaches from Acoustic Features to Deep Neural Networks","publication_year":2024,"publication_date":"2024-10-06","ids":{"openalex":"https://openalex.org/W4403165616","doi":"https://doi.org/10.1587/transinf.2024mui0001"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2024mui0001","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2024mui0001","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E108.D/4/E108.D_2024MUI0001/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E108.D/4/E108.D_2024MUI0001/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","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":["School of Information Science, JAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science, JAIST","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100400015","display_name":"Kai Li","orcid":"https://orcid.org/0009-0002-0751-1535"},"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":"Kai LI","raw_affiliation_strings":["School of Information Science, JAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science, JAIST","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009006485","display_name":"Anuwat Chaiwongyen","orcid":"https://orcid.org/0009-0007-3833-1111"},"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":"Anuwat CHAIWONGYEN","raw_affiliation_strings":["School of Information Science, JAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science, JAIST","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111119730","display_name":"Quoc\u2010Huy Nguyen","orcid":"https://orcid.org/0000-0003-4996-628X"},"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":"Quoc-Huy NGUYEN","raw_affiliation_strings":["School of Information Science, JAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science, JAIST","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015163401","display_name":"Khalid Zaman","orcid":"https://orcid.org/0009-0004-0809-7537"},"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":"Khalid ZAMAN","raw_affiliation_strings":["School of Information Science, JAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science, JAIST","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4458,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.90222057,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"E108.D","issue":"4","first_page":"300","last_page":"310"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8963000178337097,"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":0.8963000178337097,"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":0.8648999929428101,"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":0.8293967247009277},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.6139117479324341},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6088848114013672},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5896187424659729},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5588861703872681},{"id":"https://openalex.org/keywords/speech-perception","display_name":"Speech perception","score":0.41191643476486206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3655226230621338},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.10814157128334045},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09037184715270996}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8293967247009277},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.6139117479324341},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6088848114013672},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5896187424659729},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5588861703872681},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.41191643476486206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3655226230621338},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.10814157128334045},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09037184715270996}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2024mui0001","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2024mui0001","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E108.D/4/E108.D_2024MUI0001/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2024mui0001","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2024mui0001","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E108.D/4/E108.D_2024MUI0001/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403165616.pdf","grobid_xml":"https://content.openalex.org/works/W4403165616.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1975079546","https://openalex.org/W1987292616","https://openalex.org/W2017451273","https://openalex.org/W2035826164","https://openalex.org/W2050112415","https://openalex.org/W2091425152","https://openalex.org/W2118774185","https://openalex.org/W2126829180","https://openalex.org/W2148154194","https://openalex.org/W2478295692","https://openalex.org/W2624765617","https://openalex.org/W2747024632","https://openalex.org/W2791616807","https://openalex.org/W2914006617","https://openalex.org/W2936802426","https://openalex.org/W2944456902","https://openalex.org/W2989851933","https://openalex.org/W2996395154","https://openalex.org/W3024920698","https://openalex.org/W3026777299","https://openalex.org/W3036601975","https://openalex.org/W3093077017","https://openalex.org/W3197358873","https://openalex.org/W3198329097","https://openalex.org/W3212117663","https://openalex.org/W4221138880","https://openalex.org/W4297841233","https://openalex.org/W4312095886","https://openalex.org/W4378506723","https://openalex.org/W4385521743","https://openalex.org/W4386918931","https://openalex.org/W4388820942","https://openalex.org/W4388821440","https://openalex.org/W4391804994"],"related_works":["https://openalex.org/W2628861693","https://openalex.org/W3203087560","https://openalex.org/W4361279463","https://openalex.org/W2391251536","https://openalex.org/W105296515","https://openalex.org/W4232814730","https://openalex.org/W2975814312","https://openalex.org/W2362198218","https://openalex.org/W1997436241","https://openalex.org/W3152454717"],"abstract_inverted_index":{"Skillfully":[0],"fabricated":[1,35],"artificial":[2],"replicas":[3],"of":[4,80,116,137],"authentic":[5,51],"media":[6],"using":[7,37],"advanced":[8,38],"AI-based":[9,39],"generators":[10],"are":[11],"known":[12],"as":[13,63],"\u201cdeepfakes.\u201d":[14],"Deepfakes":[15],"have":[16],"become":[17],"a":[18],"growing":[19],"concern":[20],"due":[21],"to":[22,58,76,121],"their":[23],"increased":[24],"distribution":[25],"in":[26],"cyber-physical":[27],"spaces.":[28],"In":[29],"particular,":[30],"deepfake":[31,87,101,129],"speech,":[32],"which":[33],"is":[34],"by":[36,65],"speech":[40,52,88,102,130],"analysis/synthesis":[41],"techniques,":[42],"can":[43,55],"be":[44],"abused":[45],"for":[46,84,100,127],"spoofing":[47],"and":[48,68,97,104,108,124,140],"tampering":[49],"with":[50],"signals.":[53],"This":[54],"enable":[56],"attackers":[57],"commit":[59],"serious":[60],"offenses":[61],"such":[62],"fraud":[64],"voice":[66],"impersonation":[67],"unauthorized":[69],"speaker":[70],"verification.":[71],"Our":[72],"research":[73],"project":[74],"aims":[75],"construct":[77],"the":[78,114,117],"basis":[79,115],"auditory-media":[81,133],"signal":[82,134],"processing":[83,135],"defending":[85],"against":[86],"attacks.":[89],"To":[90],"this":[91],"end,":[92],"we":[93],"introduce":[94,113],"current":[95,106],"challenges":[96],"state-of-the-art":[98],"techniques":[99],"detection":[103],"examine":[105],"trends":[107],"remaining":[109],"issues.":[110],"We":[111],"then":[112],"acoustical":[118],"features":[119,139],"related":[120],"auditory":[122],"perception":[123],"propose":[125],"methods":[126],"detecting":[128],"based":[131],"on":[132],"consisting":[136],"these":[138],"deep":[141],"neural":[142],"networks":[143],"(DNNs).":[144]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2024-10-07T00:00:00"}