{"id":"https://openalex.org/W4392903644","doi":"https://doi.org/10.1109/icassp48485.2024.10448453","title":"HM-CONFORMER: A Conformer-Based Audio Deepfake Detection System with Hierarchical Pooling and Multi-Level Classification Token Aggregation Methods","display_name":"HM-CONFORMER: A Conformer-Based Audio Deepfake Detection System with Hierarchical Pooling and Multi-Level Classification Token Aggregation Methods","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903644","doi":"https://doi.org/10.1109/icassp48485.2024.10448453"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448453","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448453","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5006973604","display_name":"Hyun-seo Shin","orcid":"https://orcid.org/0009-0005-6022-7674"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hyun-seo Shin","raw_affiliation_strings":["University of Seoul,School of Computer Science","School of Computer Science, University of Seoul"],"affiliations":[{"raw_affiliation_string":"University of Seoul,School of Computer Science","institution_ids":["https://openalex.org/I124633538"]},{"raw_affiliation_string":"School of Computer Science, University of Seoul","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046942516","display_name":"Jungwoo Heo","orcid":"https://orcid.org/0009-0008-7977-2789"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jungwoo Heo","raw_affiliation_strings":["University of Seoul,School of Computer Science","School of Computer Science, University of Seoul"],"affiliations":[{"raw_affiliation_string":"University of Seoul,School of Computer Science","institution_ids":["https://openalex.org/I124633538"]},{"raw_affiliation_string":"School of Computer Science, University of Seoul","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101866564","display_name":"Ju-ho Kim","orcid":"https://orcid.org/0009-0001-4055-4564"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ju-ho Kim","raw_affiliation_strings":["University of Seoul,School of Computer Science","School of Computer Science, University of Seoul"],"affiliations":[{"raw_affiliation_string":"University of Seoul,School of Computer Science","institution_ids":["https://openalex.org/I124633538"]},{"raw_affiliation_string":"School of Computer Science, University of Seoul","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036516187","display_name":"Chan-yeong Lim","orcid":"https://orcid.org/0009-0001-6671-5004"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chan-yeong Lim","raw_affiliation_strings":["University of Seoul,School of Computer Science","School of Computer Science, University of Seoul"],"affiliations":[{"raw_affiliation_string":"University of Seoul,School of Computer Science","institution_ids":["https://openalex.org/I124633538"]},{"raw_affiliation_string":"School of Computer Science, University of Seoul","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109692709","display_name":"Wonbin Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wonbin Kim","raw_affiliation_strings":["University of Seoul,School of Computer Science","School of Computer Science, University of Seoul"],"affiliations":[{"raw_affiliation_string":"University of Seoul,School of Computer Science","institution_ids":["https://openalex.org/I124633538"]},{"raw_affiliation_string":"School of Computer Science, University of Seoul","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030475312","display_name":"Ha-Jin Yu","orcid":"https://orcid.org/0000-0003-3657-0665"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ha-Jin Yu","raw_affiliation_strings":["University of Seoul,School of Computer Science","School of Computer Science, University of Seoul"],"affiliations":[{"raw_affiliation_string":"University of Seoul,School of Computer Science","institution_ids":["https://openalex.org/I124633538"]},{"raw_affiliation_string":"School of Computer Science, University of Seoul","institution_ids":["https://openalex.org/I124633538"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5006973604"],"corresponding_institution_ids":["https://openalex.org/I124633538"],"apc_list":null,"apc_paid":null,"fwci":4.974,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.95619524,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10581","last_page":"10585"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9962000250816345,"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":0.9922999739646912,"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/conformational-isomerism","display_name":"Conformational isomerism","score":0.8334760665893555},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.8313428163528442},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8146601915359497},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6197879314422607},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5952451229095459},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5195181965827942},{"id":"https://openalex.org/keywords/spoofing-attack","display_name":"Spoofing attack","score":0.4449310004711151},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4062660336494446},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3936053514480591},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32363784313201904},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.10782387852668762},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.08557528257369995},{"id":"https://openalex.org/keywords/molecule","display_name":"Molecule","score":0.07088834047317505}],"concepts":[{"id":"https://openalex.org/C18705241","wikidata":"https://www.wikidata.org/wiki/Q1128023","display_name":"Conformational isomerism","level":3,"score":0.8334760665893555},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.8313428163528442},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8146601915359497},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6197879314422607},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5952451229095459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5195181965827942},{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.4449310004711151},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4062660336494446},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3936053514480591},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32363784313201904},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.10782387852668762},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.08557528257369995},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.07088834047317505},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448453","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448453","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2765833400","https://openalex.org/W2896457183","https://openalex.org/W2907101105","https://openalex.org/W2936774411","https://openalex.org/W3024869864","https://openalex.org/W3033188311","https://openalex.org/W3097244734","https://openalex.org/W3097777922","https://openalex.org/W3127781933","https://openalex.org/W3129918528","https://openalex.org/W3158663310","https://openalex.org/W3163842642","https://openalex.org/W3177067699","https://openalex.org/W3197358873","https://openalex.org/W3198329097","https://openalex.org/W3199131409","https://openalex.org/W3201773091","https://openalex.org/W3206479921","https://openalex.org/W4214633470","https://openalex.org/W4226013277","https://openalex.org/W4293363567","https://openalex.org/W4301373694","https://openalex.org/W4375869126","https://openalex.org/W6745378982","https://openalex.org/W6779089016","https://openalex.org/W6795807602","https://openalex.org/W6805710207"],"related_works":["https://openalex.org/W2023036309","https://openalex.org/W1972863456","https://openalex.org/W2089371831","https://openalex.org/W2052399476","https://openalex.org/W2810163160","https://openalex.org/W3083970380","https://openalex.org/W2037964119","https://openalex.org/W4220905048","https://openalex.org/W4385077663","https://openalex.org/W838464343"],"abstract_inverted_index":{"Audio":[0],"deepfake":[1],"detection":[2],"(ADD)":[3],"is":[4],"the":[5,36,42,56,89,133],"task":[6],"of":[7,46],"detecting":[8],"spoofing":[9,119],"attacks":[10],"generated":[11],"by":[12,79,121],"text-to-speech":[13],"or":[14,33],"voice":[15],"conversion":[16],"systems.":[17,149],"Spoofing":[18],"evidence,":[19],"which":[20,44],"helps":[21],"to":[22,66,92,105,112,147],"distinguish":[23],"between":[24],"spoofed":[25],"and":[26,48,126],"bona-fide":[27],"utterances,":[28],"might":[29],"exist":[30],"either":[31],"locally":[32],"globally":[34],"in":[35],"input":[37],"features.":[38],"To":[39,72],"capture":[40],"these,":[41],"Conformer,":[43],"consists":[45],"Transformers":[47],"CNN,":[49],"possesses":[50],"a":[51,140],"suitable":[52],"structure.":[53],"However,":[54],"since":[55],"Conformer":[57],"was":[58],"designed":[59],"for":[60],"sequence-to-sequence":[61],"tasks,":[62],"its":[63],"direct":[64],"application":[65],"ADD":[67],"tasks":[68],"may":[69],"be":[70],"sub-optimal.":[71],"tackle":[73],"this":[74],"limitation,":[75],"we":[76],"propose":[77],"HM-Conformer":[78,115,138],"adopting":[80],"two":[81],"components:":[82],"(1)":[83],"Hierarchical":[84],"pooling":[85],"method":[86,101],"progressively":[87],"reducing":[88],"sequence":[90,124],"length":[91],"eliminate":[93],"duplicated":[94],"information":[95,107],"(2)":[96],"Multi-level":[97],"classification":[98,103],"token":[99],"aggregation":[100],"utilizing":[102],"tokens":[104],"gather":[106],"from":[108],"different":[109],"blocks.":[110],"Owing":[111],"these":[113],"components,":[114],"can":[116],"efficiently":[117],"detect":[118],"evidence":[120],"processing":[122],"various":[123],"lengths":[125],"aggregating":[127],"them.":[128],"In":[129],"experimental":[130],"results":[131],"on":[132],"ASVspoof":[134],"2021":[135],"Deepfake":[136],"dataset,":[137],"achieved":[139],"15.71%":[141],"EER,":[142],"showing":[143],"competitive":[144],"performance":[145],"compared":[146],"recent":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":5}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
