{"id":"https://openalex.org/W7125949704","doi":"https://doi.org/10.1109/smc58881.2025.11343334","title":"Phonetic Analysis of Real and Synthetic Speech Using HuBERT Embeddings: Perspectives for Deepfake Detection","display_name":"Phonetic Analysis of Real and Synthetic Speech Using HuBERT Embeddings: Perspectives for Deepfake Detection","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125949704","doi":"https://doi.org/10.1109/smc58881.2025.11343334"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-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/A5124141305","display_name":"Dia Elhak Temmar","orcid":null},"institutions":[{"id":"https://openalex.org/I319074055","display_name":"C\u00e9gep de l'Outaouais","ror":"https://ror.org/05rxd1q58","country_code":"CA","type":"education","lineage":["https://openalex.org/I319074055"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Dia Elhak Temmar","raw_affiliation_strings":["Université du Québec en Outaouais,Gatineau,Canada"],"affiliations":[{"raw_affiliation_string":"Université du Québec en Outaouais,Gatineau,Canada","institution_ids":["https://openalex.org/I319074055"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027002286","display_name":"Assia Hamadene","orcid":null},"institutions":[{"id":"https://openalex.org/I319074055","display_name":"C\u00e9gep de l'Outaouais","ror":"https://ror.org/05rxd1q58","country_code":"CA","type":"education","lineage":["https://openalex.org/I319074055"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Assia Hamadene","raw_affiliation_strings":["Université du Québec en Outaouais,Gatineau,Canada"],"affiliations":[{"raw_affiliation_string":"Université du Québec en Outaouais,Gatineau,Canada","institution_ids":["https://openalex.org/I319074055"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124136630","display_name":"Vamshi Nallaguntla","orcid":null},"institutions":[{"id":"https://openalex.org/I39587148","display_name":"Wichita State University","ror":"https://ror.org/00c4e7y75","country_code":"US","type":"education","lineage":["https://openalex.org/I39587148"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vamshi Nallaguntla","raw_affiliation_strings":["Wichita State University,Wichita,Kansas,United States"],"affiliations":[{"raw_affiliation_string":"Wichita State University,Wichita,Kansas,United States","institution_ids":["https://openalex.org/I39587148"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124057093","display_name":"Aishwarya Fursule","orcid":null},"institutions":[{"id":"https://openalex.org/I39587148","display_name":"Wichita State University","ror":"https://ror.org/00c4e7y75","country_code":"US","type":"education","lineage":["https://openalex.org/I39587148"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aishwarya Fursule","raw_affiliation_strings":["Wichita State University,Wichita,Kansas,United States"],"affiliations":[{"raw_affiliation_string":"Wichita State University,Wichita,Kansas,United States","institution_ids":["https://openalex.org/I39587148"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124055356","display_name":"Mohand Sa\u00efd Allili","orcid":null},"institutions":[{"id":"https://openalex.org/I319074055","display_name":"C\u00e9gep de l'Outaouais","ror":"https://ror.org/05rxd1q58","country_code":"CA","type":"education","lineage":["https://openalex.org/I319074055"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mohand Sa\u00efd Allili","raw_affiliation_strings":["Université du Québec en Outaouais,Gatineau,Canada"],"affiliations":[{"raw_affiliation_string":"Université du Québec en Outaouais,Gatineau,Canada","institution_ids":["https://openalex.org/I319074055"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068051036","display_name":"Shruti Kshirsagar","orcid":"https://orcid.org/0000-0002-7191-4251"},"institutions":[{"id":"https://openalex.org/I39587148","display_name":"Wichita State University","ror":"https://ror.org/00c4e7y75","country_code":"US","type":"education","lineage":["https://openalex.org/I39587148"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shruti Kshirsagar","raw_affiliation_strings":["Wichita State University,Wichita,Kansas,United States"],"affiliations":[{"raw_affiliation_string":"Wichita State University,Wichita,Kansas,United States","institution_ids":["https://openalex.org/I39587148"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009407218","display_name":"Anderson R. Avila","orcid":"https://orcid.org/0000-0002-3088-5116"},"institutions":[{"id":"https://openalex.org/I39481719","display_name":"Institut National de la Recherche Scientifique","ror":"https://ror.org/04td37d32","country_code":"CA","type":"education","lineage":["https://openalex.org/I39481719","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Anderson R. Avila","raw_affiliation_strings":["Institutnational De La Recherche Scientifique (INRS-EMT),Montréal,Canada"],"affiliations":[{"raw_affiliation_string":"Institutnational De La Recherche Scientifique (INRS-EMT),Montréal,Canada","institution_ids":["https://openalex.org/I39481719"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5124141305"],"corresponding_institution_ids":["https://openalex.org/I319074055"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8722959,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"86","last_page":"91"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6973999738693237,"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":0.6973999738693237,"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":0.04349999874830246,"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":0.03269999846816063,"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/speech-synthesis","display_name":"Speech synthesis","score":0.5647000074386597},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.5024999976158142},{"id":"https://openalex.org/keywords/sophistication","display_name":"Sophistication","score":0.4499000012874603},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.40070000290870667},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.3790999948978424},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.35589998960494995},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.337799996137619}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7156000137329102},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6904000043869019},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5647000074386597},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.5024999976158142},{"id":"https://openalex.org/C168725872","wikidata":"https://www.wikidata.org/wiki/Q991663","display_name":"Sophistication","level":2,"score":0.4499000012874603},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.40070000290870667},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.375},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34299999475479126},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.337799996137619},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3280999958515167},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.29030001163482666},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2630000114440918}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7237353920936584,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2069355054","https://openalex.org/W2176804518","https://openalex.org/W2747874407","https://openalex.org/W2963300588","https://openalex.org/W3196667132","https://openalex.org/W3197358873","https://openalex.org/W3209059054","https://openalex.org/W4221138880"],"related_works":[],"abstract_inverted_index":{"The":[0,142],"growing":[1],"sophistication":[2],"of":[3,60,80,107,174,223,248],"speech":[4,30,84,99,113,136,140],"generated":[5,116],"by":[6],"Artificial":[7],"Intelligence":[8],"(AI)":[9],"has":[10],"introduced":[11],"new":[12],"challenges":[13],"in":[14],"audio":[15],"deepfake":[16,254],"detection.":[17,255],"Text-to-speech":[18],"(TTS)":[19],"and":[20,34,82,87,97,120,128,176,205,215],"voice":[21,42],"conversion":[22],"(VC)":[23],"technologies":[24],"can":[25,66,244],"now":[26],"produce":[27],"convincing":[28],"synthetic":[29,64,83,98,175,184,206],"with":[31,190,236],"high":[32],"quality":[33],"intelligibility.":[35],"This":[36],"poses":[37],"a":[38,92,105,134,221],"serious":[39],"threat":[40],"to":[41,57,69,138,152,157,182,201],"biometric":[43],"security":[44],"systems,":[45],"such":[46],"as":[47],"automatic":[48],"speaker":[49],"recognition.":[50],"It":[51],"also":[52,195],"increases":[53],"the":[54,58,108,158,167,172,211,237,242,249],"risks":[55],"associated":[56],"spread":[59],"spoken":[61],"disinformation,":[62],"where":[63],"voices":[65],"be":[67,245],"used":[68],"disseminate":[70],"malicious":[71],"content.":[72],"In":[73],"this":[74,146],"study,":[75],"we":[76],"conduct":[77],"an":[78,246],"analysis":[79,163],"real":[81,96,177,192,204],"at":[85],"phonetic":[86],"word":[88],"levels.":[89],"For":[90],"that,":[91],"parallel":[93],"dataset":[94],"comprising":[95],"signals":[100],"were":[101,115],"developed":[102],"based":[103,165,186],"on":[104,166,187],"subset":[106],"LibriSpeech":[109],"ASR":[110],"corpus.":[111],"Synthetic":[112],"samples":[114],"using":[117,145],"two":[118],"TTS":[119],"one":[121],"VC":[122],"systems:":[123],"Coqui":[124],"TTS,":[125,127],"VITS":[126],"StarGANv2":[129],"VC.":[130],"We":[131,194,208],"adopted":[132],"HuBERT,":[133],"self-supervised":[135],"model,":[137],"extract":[139],"embeddings.":[141],"motivation":[143],"for":[144,253],"model":[147],"stems":[148],"from":[149],"its":[150],"ability":[151],"recognize":[153],"sound":[154],"units":[155],"corresponding":[156],"so-called":[159],"pseudo":[160],"phonemes.":[161],"Our":[162],"is":[164],"KL":[168],"divergence":[169],"(KLD)":[170],"between":[171,203,213],"distributions":[173],"phonemes,":[178],"which":[179],"allowed":[180],"us":[181],"rank":[183],"phonemes":[185,224,252],"their":[188,191],"alignment":[189],"counterpart.":[193],"trained":[196],"several":[197],"classifiers":[198],"per":[199,217],"phoneme":[200],"distinguish":[202],"samples.":[207],"then":[209],"compute":[210],"correlations":[212],"KLD":[214,243],"accuracies":[216],"phoneme.":[218],"Besides":[219],"showing":[220],"list":[222],"that":[225,232,241],"are":[226],"more":[227],"discriminative,":[228],"our":[229],"findings":[230],"suggest":[231],"vowels":[233],"correlate":[234],"better":[235],"classifiers\u2019":[238],"performance,":[239],"suggesting":[240],"indicator":[247],"most":[250],"distinguishable":[251]},"counts_by_year":[],"updated_date":"2026-01-29T23:17:01.242718","created_date":"2026-01-29T00:00:00"}