{"id":"https://openalex.org/W4210730577","doi":"https://doi.org/10.1109/asru51503.2021.9688312","title":"Using Self Attention DNNs to Discover Phonemic Features for Audio Deep Fake Detection","display_name":"Using Self Attention DNNs to Discover Phonemic Features for Audio Deep Fake Detection","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4210730577","doi":"https://doi.org/10.1109/asru51503.2021.9688312"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688312","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5074132219","display_name":"Hira Dhamyal","orcid":null},"institutions":[{"id":"https://openalex.org/I207789805","display_name":"Lahore University of Management Sciences","ror":"https://ror.org/05b5x4a35","country_code":"PK","type":"education","lineage":["https://openalex.org/I207789805"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"Hira Dhamyal","raw_affiliation_strings":["Lahore University of Management Sciences"],"affiliations":[{"raw_affiliation_string":"Lahore University of Management Sciences","institution_ids":["https://openalex.org/I207789805"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084749426","display_name":"Ayesha Ali","orcid":"https://orcid.org/0000-0003-1051-2264"},"institutions":[{"id":"https://openalex.org/I207789805","display_name":"Lahore University of Management Sciences","ror":"https://ror.org/05b5x4a35","country_code":"PK","type":"education","lineage":["https://openalex.org/I207789805"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Ayesha Ali","raw_affiliation_strings":["Lahore University of Management Sciences"],"affiliations":[{"raw_affiliation_string":"Lahore University of Management Sciences","institution_ids":["https://openalex.org/I207789805"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079017254","display_name":"Ihsan Ayyub Qazi","orcid":"https://orcid.org/0000-0002-2262-0353"},"institutions":[{"id":"https://openalex.org/I207789805","display_name":"Lahore University of Management Sciences","ror":"https://ror.org/05b5x4a35","country_code":"PK","type":"education","lineage":["https://openalex.org/I207789805"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Ihsan Ayyub Qazi","raw_affiliation_strings":["Lahore University of Management Sciences"],"affiliations":[{"raw_affiliation_string":"Lahore University of Management Sciences","institution_ids":["https://openalex.org/I207789805"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038004767","display_name":"Agha Ali Raza","orcid":"https://orcid.org/0000-0003-0124-9783"},"institutions":[{"id":"https://openalex.org/I207789805","display_name":"Lahore University of Management Sciences","ror":"https://ror.org/05b5x4a35","country_code":"PK","type":"education","lineage":["https://openalex.org/I207789805"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Agha Ali Raza","raw_affiliation_strings":["Lahore University of Management Sciences"],"affiliations":[{"raw_affiliation_string":"Lahore University of Management Sciences","institution_ids":["https://openalex.org/I207789805"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5074132219"],"corresponding_institution_ids":["https://openalex.org/I207789805"],"apc_list":null,"apc_paid":null,"fwci":0.381,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.62715935,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1178","last_page":"1184"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9991999864578247,"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":0.9972000122070312,"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":0.7879029512405396},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7528926134109497},{"id":"https://openalex.org/keywords/spoofing-attack","display_name":"Spoofing attack","score":0.6651187539100647},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.543443500995636},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4679884612560272},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.4660175144672394},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4591303765773773},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44563767313957214},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33589887619018555}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7879029512405396},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7528926134109497},{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.6651187539100647},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.543443500995636},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4679884612560272},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.4660175144672394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4591303765773773},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44563767313957214},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33589887619018555},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9688312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688312","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1965672907","https://openalex.org/W1972231470","https://openalex.org/W1980549382","https://openalex.org/W2026741936","https://openalex.org/W2057850904","https://openalex.org/W2138878452","https://openalex.org/W2303197844","https://openalex.org/W2327501763","https://openalex.org/W2488426223","https://openalex.org/W2602814339","https://openalex.org/W2884483159","https://openalex.org/W2889519245","https://openalex.org/W2950768109","https://openalex.org/W2951025380","https://openalex.org/W2963420686","https://openalex.org/W2973181078","https://openalex.org/W2982436869","https://openalex.org/W2984507485","https://openalex.org/W3006775364","https://openalex.org/W3024805264","https://openalex.org/W3024920698","https://openalex.org/W3026777299","https://openalex.org/W3033711348","https://openalex.org/W3039011115","https://openalex.org/W3097805260","https://openalex.org/W3102472156","https://openalex.org/W3146945401","https://openalex.org/W3197762302","https://openalex.org/W4288375408","https://openalex.org/W6761837902","https://openalex.org/W6764072591","https://openalex.org/W6769239586"],"related_works":["https://openalex.org/W1544536563","https://openalex.org/W2060836468","https://openalex.org/W4280646740","https://openalex.org/W2608841979","https://openalex.org/W2004780548","https://openalex.org/W2748448327","https://openalex.org/W2772709568","https://openalex.org/W2004415003","https://openalex.org/W2088222388","https://openalex.org/W2786684668"],"abstract_inverted_index":{"With":[0],"the":[1,35,85,125,129,134,143,173],"advancement":[2],"in":[3,93,108],"natural-sounding":[4],"speech":[5,21,31],"production":[6],"models,":[7],"it":[8],"is":[9],"becoming":[10],"important":[11],"to":[12,52,80],"develop":[13],"models":[14,22,76],"that":[15,50,74,142],"can":[16],"detect":[17],"spoofed":[18,111],"audios.":[19],"Synthesized":[20],"do":[23],"not":[24,78],"explicitly":[25],"account":[26],"for":[27,137],"all":[28],"factors":[29],"affecting":[30],"production,":[32],"such":[33,90,102],"as":[34,82,84],"shape,":[36],"size":[37],"and":[38,61,68,89,104,112,123,140,155,165],"structure":[39],"of":[40,55,63,128],"a":[41,117],"speaker's":[42],"vocal":[43],"tract.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,115,159],"hypothesize":[49],"due":[51],"practical":[53],"limitations":[54],"audio":[56],"corpora":[57],"(including":[58],"size,":[59],"distribution,":[60],"balance":[62],"variables":[64],"like":[65],"gender,":[66],"age,":[67],"accents),":[69],"there":[70],"exist":[71],"certain":[72],"phonemes":[73,91,103,177],"synthesized":[75],"are":[77,188],"able":[79],"replicate":[81],"well":[83],"human":[86],"articulation":[87],"system":[88],"differ":[92],"their":[94,106],"spectral":[95],"characteristics":[96],"from":[97,178],"bonafide":[98,113],"speech.":[99],"To":[100],"discover":[101],"quantify":[105],"effectiveness":[107],"distinguishing":[109],"between":[110],"speech,":[114],"use":[116,133],"deep":[118],"learning":[119],"model":[120],"with":[121],"self-attention,":[122],"analyze":[124],"attention":[126,144],"weights":[127],"trained":[130],"model.":[131],"We":[132],"ASVSpoof2019":[135],"dataset":[136],"our":[138],"analysis":[139],"find":[141],"mechanism":[145],"picks":[146],"most":[147,175],"on":[148,163,167],"fricatives:":[149],"/S/,/SH/,":[150],"nasals:":[151],"/M/,/N/,":[152],"vowels:":[153],"/Y/,":[154],"stops:":[156],"/D/.":[157],"Furthermore,":[158],"obtain":[160],"7.54%":[161],"EER":[162],"train":[164],"11.98%":[166],"dev":[168],"data":[169],"when":[170,183],"using":[171],"only":[172],"top-16":[174],"attended":[176],"input":[179],"audio,":[180],"better":[181],"than":[182],"any":[184],"other":[185],"phoneme":[186],"classes":[187],"used.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}