{"id":"https://openalex.org/W4379046716","doi":"https://doi.org/10.1145/3592572.3592841","title":"SpoTNet: A spoofing-aware Transformer Network for Effective Synthetic Speech Detection","display_name":"SpoTNet: A spoofing-aware Transformer Network for Effective Synthetic Speech Detection","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4379046716","doi":"https://doi.org/10.1145/3592572.3592841"},"language":"en","primary_location":{"id":"doi:10.1145/3592572.3592841","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3592572.3592841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM International Workshop on Multimedia AI against Disinformation","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/A5005432885","display_name":"Awais Khan","orcid":"https://orcid.org/0000-0003-2497-7687"},"institutions":[{"id":"https://openalex.org/I177721651","display_name":"Oakland University","ror":"https://ror.org/01ythxj32","country_code":"US","type":"education","lineage":["https://openalex.org/I177721651"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Awais Khan","raw_affiliation_strings":["Department of Computer Science & Engineering, Oakland University, USA"],"raw_orcid":"https://orcid.org/0000-0003-2497-7687","affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, Oakland University, USA","institution_ids":["https://openalex.org/I177721651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024102795","display_name":"Khalid Mahmood Malik","orcid":"https://orcid.org/0000-0002-7927-3436"},"institutions":[{"id":"https://openalex.org/I177721651","display_name":"Oakland University","ror":"https://ror.org/01ythxj32","country_code":"US","type":"education","lineage":["https://openalex.org/I177721651"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khalid Mahmood Malik","raw_affiliation_strings":["Department of Computer Science & Engineering, Oakland University, USA"],"raw_orcid":"https://orcid.org/0000-0002-7927-3436","affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, Oakland University, USA","institution_ids":["https://openalex.org/I177721651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9369,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.92614511,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10","last_page":"18"},"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":0.9991000294685364,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spoofing-attack","display_name":"Spoofing attack","score":0.828809380531311},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7857649922370911},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6839253902435303},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.617872953414917},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5466859340667725},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.48761454224586487},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.47719821333885193},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.44368258118629456},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4025173485279083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4021375775337219},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09435513615608215}],"concepts":[{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.828809380531311},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7857649922370911},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6839253902435303},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.617872953414917},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5466859340667725},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.48761454224586487},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.47719821333885193},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.44368258118629456},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4025173485279083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4021375775337219},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09435513615608215},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3592572.3592841","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3592572.3592841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM International Workshop on Multimedia AI against Disinformation","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G4550692654","display_name":null,"funder_award_id":"1815724","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2155144927","https://openalex.org/W2403139431","https://openalex.org/W2747872086","https://openalex.org/W2979826702","https://openalex.org/W2995655945","https://openalex.org/W3089349122","https://openalex.org/W3095291040","https://openalex.org/W3118286613","https://openalex.org/W3127781933","https://openalex.org/W3157576687","https://openalex.org/W3158663310","https://openalex.org/W3160325739","https://openalex.org/W3161011913","https://openalex.org/W3163596559","https://openalex.org/W3185259378","https://openalex.org/W3198486673","https://openalex.org/W4210305678","https://openalex.org/W4226338771","https://openalex.org/W4285149944","https://openalex.org/W4312560592","https://openalex.org/W4323022270"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W642007152","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W1909292483","https://openalex.org/W1428730622","https://openalex.org/W596245619"],"abstract_inverted_index":{"The":[0,43,114,214],"prevalence":[1],"of":[2,65,147,167,229,242],"voice":[3,22,36,60],"spoofing":[4,92,99,110,125],"attacks":[5],"in":[6,46,85,161,210],"today\u2019s":[7],"digital":[8],"world":[9],"has":[10],"become":[11],"a":[12,51,73],"critical":[13],"security":[14,56],"concern.":[15],"Attackers":[16],"employ":[17],"various":[18],"techniques,":[19],"such":[20],"as":[21,131],"conversion":[23],"(VC)":[24],"and":[25,37,101,189,198,245],"text-to-speech":[26],"(TTS),":[27],"to":[28,40,54,127,153,173,207,238],"generate":[29],"synthetic":[30,47,80,137,149,211],"speech":[31,48,81,129,150,169,212],"that":[32,95],"imitates":[33],"the":[34,107,122,141,144,148,155,164,168,175,187,194,232,240],"victim\u2019s":[35],"gain":[38],"access":[39,78],"sensitive":[41],"information.":[42],"recent":[44,222],"advances":[45],"generation":[49],"pose":[50],"significant":[52],"threat":[53],"modern":[55],"systems,":[57],"while":[58,160],"traditional":[59],"authentication":[61],"methods":[62,225],"are":[63,151],"incapable":[64],"detecting":[66],"them":[67],"effectively.":[68],"To":[69],"address":[70],"this":[71,86,184],"issue,":[72],"novel":[74],"solution":[75,216],"for":[76],"logical":[77,109],"(LA)-based":[79],"detection":[82],"is":[83,89,171],"proposed":[84,123,215],"paper.":[87],"SpoTNet":[88],"an":[90,202],"attention-based":[91],"transformer":[93,111],"network":[94],"includes":[96],"crafted":[97,191],"front-end":[98],"features":[100,104,117],"deep":[102],"attentive":[103,116],"retrieved":[105],"using":[106],"developed":[108],"encoder":[112],"(LSTE).":[113],"derived":[115],"were":[118],"then":[119],"processed":[120],"by":[121,140],"multi-layer":[124],"classifier":[126],"classify":[128],"samples":[130],"bona":[132],"fide":[133],"or":[134],"synthetic.":[135],"In":[136],"speeches":[138],"produced":[139],"TTS":[142],"algorithm,":[143],"spectral":[145,196,199],"characteristics":[146],"altered":[152],"match":[154],"target":[156,176],"speaker\u2019s":[157,177],"formant":[158],"frequencies,":[159],"VC":[162],"attacks,":[163],"temporal":[165],"alignment":[166],"segments":[170],"manipulated":[172],"preserve":[174],"prosodic":[178,188],"features.":[179],"By":[180],"highlighting":[181],"these":[182],"observations,":[183],"paper":[185],"targets":[186],"phonetic-based":[190],"features,":[192],"i.e.,":[193],"Mel-spectrogram,":[195],"contrast,":[197],"envelope,":[200],"presenting":[201],"effective":[203,209],"preprocessing":[204],"pipeline":[205],"proven":[206],"be":[208],"detection.":[213],"achieved":[217],"state-of-the-art":[218],"performance":[219],"against":[220],"eight":[221],"feature":[223],"fusion":[224],"with":[226],"lower":[227],"EER":[228],"0.95%":[230],"on":[231],"ASVspoof-LA":[233],"dataset,":[234],"demonstrating":[235],"its":[236],"potential":[237],"advance":[239],"field":[241],"speaker":[243,247],"identification":[244],"improve":[246],"recognition":[248],"systems.":[249]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}