{"id":"https://openalex.org/W4388820942","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317309","title":"Analysis of Spectro-Temporal Modulation Representation for Deep-Fake Speech Detection","display_name":"Analysis of Spectro-Temporal Modulation Representation for Deep-Fake Speech Detection","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388820942","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317309"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc58517.2023.10317309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5109540851","display_name":"Haowei Cheng","orcid":"https://orcid.org/0009-0008-2265-6437"},"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":"Haowei Cheng","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology,Ishikawa,Japan,923-1292"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology,Ishikawa,Japan,923-1292","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005680805","display_name":"Candy Olivia Mawalim","orcid":"https://orcid.org/0000-0001-9853-8893"},"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":"Candy Olivia Mawalim","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology,Ishikawa,Japan,923-1292"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology,Ishikawa,Japan,923-1292","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":["Japan Advanced Institute of Science and Technology,Ishikawa,Japan,923-1292"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology,Ishikawa,Japan,923-1292","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024024966","display_name":"Lijun Wang","orcid":"https://orcid.org/0009-0001-6655-4116"},"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":"Lijun Wang","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology,Ishikawa,Japan,923-1292"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology,Ishikawa,Japan,923-1292","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":["Japan Advanced Institute of Science and Technology,Ishikawa,Japan,923-1292"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology,Ishikawa,Japan,923-1292","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177738480"],"apc_list":null,"apc_paid":null,"fwci":0.9667,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77858482,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1822","last_page":"1829"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9966999888420105,"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/computer-science","display_name":"Computer science","score":0.7975016832351685},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7332354784011841},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6770414710044861},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5537077188491821},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5289737582206726},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5176901817321777},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4816285967826843},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.4731522500514984},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.46439605951309204},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4377293884754181},{"id":"https://openalex.org/keywords/spoofing-attack","display_name":"Spoofing attack","score":0.4244576692581177},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42097777128219604},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.41494864225387573},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.07496529817581177}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7975016832351685},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7332354784011841},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6770414710044861},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5537077188491821},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5289737582206726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5176901817321777},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4816285967826843},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.4731522500514984},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.46439605951309204},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4377293884754181},{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.4244576692581177},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42097777128219604},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.41494864225387573},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.07496529817581177},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc58517.2023.10317309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6499999761581421}],"awards":[{"id":"https://openalex.org/G3635912132","display_name":"VOICE 2.0: towards augmentation of enriched speech communication","funder_award_id":"20KK0233","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4133580503","display_name":null,"funder_award_id":"23H04344","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1991716120","https://openalex.org/W2008806652","https://openalex.org/W2030144871","https://openalex.org/W2047596842","https://openalex.org/W2054139811","https://openalex.org/W2054883573","https://openalex.org/W2101230918","https://openalex.org/W2122516409","https://openalex.org/W2128681980","https://openalex.org/W2129486313","https://openalex.org/W2171687003","https://openalex.org/W2784941364","https://openalex.org/W2931977246","https://openalex.org/W2936802426","https://openalex.org/W2948163068","https://openalex.org/W2950733131","https://openalex.org/W2951639392","https://openalex.org/W2967606780","https://openalex.org/W2972614582","https://openalex.org/W2972786657","https://openalex.org/W3026777299","https://openalex.org/W3097681707","https://openalex.org/W3160325739","https://openalex.org/W3164861235","https://openalex.org/W3193745889","https://openalex.org/W3197184958","https://openalex.org/W4220832730","https://openalex.org/W4221138880","https://openalex.org/W4223915588","https://openalex.org/W4226264925","https://openalex.org/W4226346368","https://openalex.org/W4307877759","https://openalex.org/W4313224733","https://openalex.org/W4378506723","https://openalex.org/W6852755086"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2294333436","https://openalex.org/W2955597484","https://openalex.org/W2373767407","https://openalex.org/W2653598178","https://openalex.org/W3110551121","https://openalex.org/W2747006289","https://openalex.org/W3160071434","https://openalex.org/W2851491717"],"abstract_inverted_index":{"Deep-fake":[0],"speech":[1,11,30,45,73,84,194],"detection":[2],"aims":[3],"to":[4,39,47,56,70,133],"develop":[5],"effective":[6],"techniques":[7],"for":[8,54,63,143],"identifying":[9],"fake":[10,29,44,104,118],"generated":[12],"using":[13],"advanced":[14],"deep-learning":[15],"methods.":[16],"It":[17],"can":[18,36],"reduce":[19],"the":[20,93,98,122,128,149,153,164,190],"negative":[21],"impact":[22],"of":[23,28,152,176],"malicious":[24],"production":[25],"or":[26],"dissemination":[27],"in":[31,83,88,115,199],"real-life":[32],"scenarios.":[33],"Although":[34],"humans":[35],"relatively":[37],"easy":[38],"distinguish":[40,57,189],"between":[41,101],"genuine":[42,102,116,191],"and":[43,103,117,157,163,178,192,195],"due":[46],"human":[48,76,123],"auditory":[49,124],"mechanisms,":[50],"it":[51],"is":[52,66],"difficult":[53],"machines":[55,68],"them":[58],"correctly.":[59],"One":[60],"major":[61],"reason":[62],"this":[64,90,108],"challenge":[65],"that":[67,184],"struggle":[69],"effectively":[71],"separate":[72],"content":[74],"from":[75,96],"vocal":[77],"system":[78],"information.":[79],"Common":[80],"features":[81],"used":[82],"processing":[85],"face":[86],"difficulties":[87],"handling":[89],"issue,":[91,109],"hindering":[92],"neural":[94,137],"network":[95,138],"learning":[97],"discriminative":[99],"differences":[100],"speech.":[105],"To":[106],"address":[107],"we":[110],"investigated":[111],"spectro-temporal":[112,129,185],"modulation":[113,130,186],"representations":[114,187],"speech,":[119],"which":[120],"simulate":[121],"perception":[125],"process.":[126],"Next,":[127],"was":[131],"fit":[132],"a":[134],"light":[135],"convolutional":[136],"bidirectional":[139],"long":[140],"short-term":[141],"memory":[142],"classification.":[144],"We":[145],"conducted":[146],"experiments":[147],"on":[148],"benchmark":[150],"datasets":[151],"Automatic":[154],"Speaker":[155],"Verification":[156],"Spoofing":[158],"Countermeasures":[159],"Challenge":[160,169],"2019":[161],"(ASVspoof2019)":[162],"Audio":[165],"Deep":[166],"synthesis":[167],"Detection":[168],"2023":[170],"(ADD2023),":[171],"achieving":[172],"an":[173],"equal-error":[174],"rate":[175],"8.33%":[177],"42.10%,":[179],"respectively.":[180],"The":[181],"results":[182],"showed":[183],"could":[188],"deep-fake":[193],"have":[196],"adequate":[197],"performance":[198],"both":[200],"datasets.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}