{"id":"https://openalex.org/W3196837826","doi":"https://doi.org/10.21437/interspeech.2021-1705","title":"Generalized Spoofing Detection Inspired from Audio Generation Artifacts","display_name":"Generalized Spoofing Detection Inspired from Audio Generation Artifacts","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3196837826","doi":"https://doi.org/10.21437/interspeech.2021-1705","mag":"3196837826"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1705","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1705","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5102873084","display_name":"Yang Gao","orcid":"https://orcid.org/0000-0003-0348-2546"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yang Gao","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109404932","display_name":"Tyler Vuong","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tyler Vuong","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083369584","display_name":"Mahsa Elyasi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mahsa Elyasi","raw_affiliation_strings":["AI Foundation, USA"],"affiliations":[{"raw_affiliation_string":"AI Foundation, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036255713","display_name":"Gaurav Bharaj","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gaurav Bharaj","raw_affiliation_strings":["AI Foundation, USA"],"affiliations":[{"raw_affiliation_string":"AI Foundation, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102775511","display_name":"Rita Singh","orcid":"https://orcid.org/0000-0003-3743-0162"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rita Singh","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102873084"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":2.6232,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.90599719,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4184","last_page":"4188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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/T10860","display_name":"Speech and Audio Processing","score":0.9983000159263611,"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":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.7644553780555725},{"id":"https://openalex.org/keywords/spoofing-attack","display_name":"Spoofing attack","score":0.7526589632034302},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43114417791366577},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4173102378845215},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37755680084228516},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.23618197441101074},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.20833885669708252},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.20747366547584534}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7644553780555725},{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.7526589632034302},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43114417791366577},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4173102378845215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37755680084228516},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.23618197441101074},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.20833885669708252},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.20747366547584534}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-1705","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1705","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1990934990","https://openalex.org/W2054139811","https://openalex.org/W2072473772","https://openalex.org/W2137075158","https://openalex.org/W2167763959","https://openalex.org/W2176804518","https://openalex.org/W2295634712","https://openalex.org/W2394783243","https://openalex.org/W2400523955","https://openalex.org/W2587891104","https://openalex.org/W2588445447","https://openalex.org/W2590129515","https://openalex.org/W2745896134","https://openalex.org/W2889084898","https://openalex.org/W2936774411","https://openalex.org/W2936802426","https://openalex.org/W2950733131","https://openalex.org/W2963609956","https://openalex.org/W2964135678","https://openalex.org/W2972786657","https://openalex.org/W2989571531","https://openalex.org/W2991318208","https://openalex.org/W2998405168","https://openalex.org/W2999174651","https://openalex.org/W3012033723","https://openalex.org/W3092967725","https://openalex.org/W3096830101","https://openalex.org/W3131786367","https://openalex.org/W3146945401","https://openalex.org/W3161761462","https://openalex.org/W3162366763","https://openalex.org/W4320013936"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2998478967","https://openalex.org/W2188559950","https://openalex.org/W2989910292","https://openalex.org/W3128793638","https://openalex.org/W2607818178","https://openalex.org/W2123299109","https://openalex.org/W2021230337","https://openalex.org/W3153057489"],"abstract_inverted_index":{"State-of-the-art":[0],"methods":[1],"for":[2,45,141,164],"audio":[3,47],"generation":[4],"suffer":[5],"from":[6],"fingerprint":[7],"artifacts":[8,17],"and":[9,14,72,78,84,102,161,168],"repeated":[10],"inconsistencies":[11],"across":[12],"temporal":[13],"spectral":[15],"domains.Such":[16],"could":[18],"be":[19],"well":[20],"captured":[21],"by":[22,115,132],"the":[23,28,46,80,104,111,128,153],"frequency":[24],"domain":[25],"analysis":[26,160],"over":[27,42],"spectrogram.Thus,":[29],"we":[30,126,144],"propose":[31],"a":[32,62,94,99,138],"novel":[33,90],"use":[34],"of":[35],"long-range":[36],"spectro-temporal":[37,124],"modulation":[38],"feature":[39,53,73,91,167],"-2D":[40],"DCT":[41,123],"log-Mel":[43,57],"spectrogram":[44],"deepfake":[48],"detection.We":[49],"show":[50],"that":[51,97],"this":[52,89],"works":[54],"better":[55],"than":[56],"spectrogram,":[58],"CQCC,":[59],"MFCC,":[60],"as":[61],"suitable":[63],"candidate":[64],"to":[65,75,134],"capture":[66],"such":[67],"artifacts.We":[68],"employ":[69],"spectrum":[70],"augmentation":[71],"normalization":[74],"decrease":[76,127],"overfitting":[77],"bridge":[79],"gap":[81],"between":[82],"training":[83],"test":[85],"dataset":[86],"along":[87],"with":[88,119],"introduction.We":[92],"developed":[93],"CNN-based":[95],"baseline":[96,118],"achieved":[98],"0.0849":[100],"t-DCF":[101,129],"outperformed":[103],"previously":[105],"top":[106],"single":[107],"systems":[108],"reported":[109],"in":[110],"ASVspoof":[112],"2019":[113],"challenge.Finally,":[114],"combining":[116],"our":[117,120,146,165],"proposed":[121,154,166],"2D":[122],"feature,":[125],"score":[130],"down":[131],"14%":[133],"0.0737,":[135],"making":[136],"it":[137],"state-of-the-art":[139],"system":[140],"spoofing":[142],"detection.Furthermore,":[143],"evaluate":[145],"model":[147],"using":[148],"two":[149],"external":[150],"datasets,":[151],"showing":[152],"feature's":[155],"generalization":[156],"ability.We":[157],"also":[158],"provide":[159],"ablation":[162],"studies":[163],"results.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}