{"id":"https://openalex.org/W4362467324","doi":"https://doi.org/10.1142/s0218001423500155","title":"Deepfake Speech Recognition and Detection","display_name":"Deepfake Speech Recognition and Detection","publication_year":2023,"publication_date":"2023-03-31","ids":{"openalex":"https://openalex.org/W4362467324","doi":"https://doi.org/10.1142/s0218001423500155"},"language":"en","primary_location":{"id":"doi:10.1142/s0218001423500155","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001423500155","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","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/A5006411115","display_name":"Hung-Chang Chang","orcid":"https://orcid.org/0000-0002-1872-4256"},"institutions":[{"id":"https://openalex.org/I75357094","display_name":"National Yunlin University of Science and Technology","ror":"https://ror.org/04qkq2m54","country_code":"TW","type":"education","lineage":["https://openalex.org/I75357094"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Hung-Chang Chang","raw_affiliation_strings":["Bachelor Program in Interdisciplinary Studies Yunlin University of Science and Technology Yunlin, Doulu, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-1872-4256","affiliations":[{"raw_affiliation_string":"Bachelor Program in Interdisciplinary Studies Yunlin University of Science and Technology Yunlin, Doulu, Taiwan","institution_ids":["https://openalex.org/I75357094"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5006411115"],"corresponding_institution_ids":["https://openalex.org/I75357094"],"apc_list":null,"apc_paid":null,"fwci":0.5044,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69490277,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"37","issue":"09","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9980000257492065,"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":0.9973000288009644,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.876800537109375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7863097190856934},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6527748703956604},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6429996490478516},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.6278966069221497},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5585564970970154},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5109900236129761},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4177000820636749},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.41401708126068115},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34299737215042114},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34235164523124695}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.876800537109375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7863097190856934},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6527748703956604},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6429996490478516},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.6278966069221497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5585564970970154},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5109900236129761},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4177000820636749},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41401708126068115},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34299737215042114},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34235164523124695},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218001423500155","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001423500155","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1485546787","https://openalex.org/W2013996527","https://openalex.org/W2052384514","https://openalex.org/W2063223471","https://openalex.org/W2064675550","https://openalex.org/W2101346879","https://openalex.org/W2129244720","https://openalex.org/W2141493634","https://openalex.org/W2142977543","https://openalex.org/W2148154194","https://openalex.org/W2150658333","https://openalex.org/W2508429489","https://openalex.org/W2583955450","https://openalex.org/W2806379360","https://openalex.org/W2808128011","https://openalex.org/W2902461656","https://openalex.org/W2920877282","https://openalex.org/W2953532875","https://openalex.org/W2963418523","https://openalex.org/W2964539095","https://openalex.org/W4205947740","https://openalex.org/W4316089280"],"related_works":["https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W2108985546","https://openalex.org/W2433276473","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W2077992636","https://openalex.org/W321304764","https://openalex.org/W1537411440"],"abstract_inverted_index":{"Deepfake":[0],"technology,":[1],"especially":[2],"deep":[3],"voice,":[4,180],"which":[5,108],"has":[6],"been":[7],"derived":[8],"from":[9],"artificial":[10],"intelligence":[11],"in":[12,54,88,192],"recent":[13],"years,":[14],"is":[15,21,102,110,126],"potentially":[16],"harmful,":[17],"and":[18,46,85,94,149,160,178,181,189],"the":[19,31,62,66,74,105,123,129,132,139,145,150,163,173,193,197,201],"public":[20],"not":[22],"yet":[23],"wary.":[24],"However,":[25],"many":[26],"speech":[27,49,116,119,140],"synthesis":[28,120],"models":[29],"measure":[30],"degree":[32],"of":[33,44,48,107,131,168,176,200],"true":[34],"restitution":[35],"by":[36,50,77,81,115],"Mean":[37],"Opinion":[38],"Rating":[39],"(MOS),":[40],"a":[41,91,95,111],"subjective":[42],"assessment":[43],"naturalness":[45],"quality":[47],"human":[51],"subjects,":[52],"but":[53],"future":[55],"it":[56],"will":[57],"be":[58],"difficult":[59],"to":[60,171,186,195],"distinguish":[61],"interlocutor\u2019s":[63],"identity":[64,134],"through":[65,135],"screen.":[67],"For":[68],"this":[69,71,78],"reason,":[70],"study":[72],"addresses":[73],"threat":[75],"posed":[76],"new":[79,202],"technology":[80],"combining":[82],"representational":[83],"learning":[84,87,147],"0transfer":[86],"two":[89],"sub-systems:":[90],"recognition":[92,100,141],"system":[93,101,125],"voice":[96,109,113,191],"print":[97],"system.":[98],"The":[99],"responsible":[103,127],"for":[104,128,158],"detection":[106],"fake":[112,179,190],"generated":[114],"conversion":[117],"or":[118],"techniques,":[121],"while":[122],"acoustic":[124,136],"verification":[130],"speaker\u2019s":[133],"features.":[137],"In":[138],"system,":[142],"we":[143],"use":[144,155,182],"representation":[146,174],"method":[148],"transfer":[151],"classification":[152],"method.":[153],"We":[154],"X-vector":[156],"data":[157,170],"training,":[159],"then":[161],"fine-tune":[162],"model":[164],"using":[165],"four":[166],"types":[167],"marker":[169],"learn":[172],"vectors":[175],"real":[177,188],"support":[183],"vector":[184],"machine":[185],"classify":[187],"back-end":[194],"reduce":[196],"negative":[198],"effect":[199],"technique.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}