{"id":"https://openalex.org/W2964002811","doi":"https://doi.org/10.1109/icassp.2019.8682640","title":"Attentive Filtering Networks for Audio Replay Attack Detection","display_name":"Attentive Filtering Networks for Audio Replay Attack Detection","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2964002811","doi":"https://doi.org/10.1109/icassp.2019.8682640","mag":"2964002811"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682640","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/243c0b00-86f3-43f6-8d44-92344fd6dc96","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010825170","display_name":"Cheng-I Lai","orcid":"https://orcid.org/0000-0002-2343-8596"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheng-I Lai","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028432601","display_name":"Alberto Abad","orcid":"https://orcid.org/0000-0003-2122-5148"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alberto Abad","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055415493","display_name":"Korin Richmond","orcid":"https://orcid.org/0000-0003-1450-8270"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Korin Richmond","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["Digital Content and Media Sciences Research Division, National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Content and Media Sciences Research Division, National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":75,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6316","last_page":"6320"},"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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":0.9987000226974487,"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":0.8828256130218506},{"id":"https://openalex.org/keywords/spoofing-attack","display_name":"Spoofing attack","score":0.8327540755271912},{"id":"https://openalex.org/keywords/replay-attack","display_name":"Replay attack","score":0.8176867961883545},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.517004132270813},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.505629301071167},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5019896030426025},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4642793536186218},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4421652853488922},{"id":"https://openalex.org/keywords/fusion-mechanism","display_name":"Fusion mechanism","score":0.42625701427459717},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.22401347756385803},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.17609500885009766}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8828256130218506},{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.8327540755271912},{"id":"https://openalex.org/C11560541","wikidata":"https://www.wikidata.org/wiki/Q1756025","display_name":"Replay attack","level":3,"score":0.8176867961883545},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.517004132270813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.505629301071167},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5019896030426025},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4642793536186218},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4421652853488922},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.42625701427459717},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.22401347756385803},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.17609500885009766},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.0},{"id":"https://openalex.org/C103038307","wikidata":"https://www.wikidata.org/wiki/Q6556360","display_name":"Lipid bilayer fusion","level":3,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2019.8682640","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/243c0b00-86f3-43f6-8d44-92344fd6dc96","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/243c0b00-86f3-43f6-8d44-92344fd6dc96","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lai, C-I, Abad, A, Richmond, K, Yamagishi, J, Dehak, N & King, S 2019, Attentive filtering networks for audio replay attack detection. in 2019 IEEE International Conference on Acoustics, Speech and Signal Processing. EEE International Conference on Acoustics, Speech, and Signal Processing, pp. 6316-6320, 44th International Conference on Acoustics, Speech, and Signal Processing, Brighton , United Kingdom, 12/05/19. https://doi.org/10.1109/ICASSP.2019.8682640","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/243c0b00-86f3-43f6-8d44-92344fd6dc96","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/243c0b00-86f3-43f6-8d44-92344fd6dc96","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lai, C-I, Abad, A, Richmond, K, Yamagishi, J, Dehak, N & King, S 2019, Attentive filtering networks for audio replay attack detection. in 2019 IEEE International Conference on Acoustics, Speech and Signal Processing. EEE International Conference on Acoustics, Speech, and Signal Processing, pp. 6316-6320, 44th International Conference on Acoustics, Speech, and Signal Processing, Brighton , United Kingdom, 12/05/19. https://doi.org/10.1109/ICASSP.2019.8682640","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/243c0b00-86f3-43f6-8d44-92344fd6dc96","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/243c0b00-86f3-43f6-8d44-92344fd6dc96","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lai, C-I, Abad, A, Richmond, K, Yamagishi, J, Dehak, N & King, S 2019, Attentive filtering networks for audio replay attack detection. in 2019 IEEE International Conference on Acoustics, Speech and Signal Processing. EEE International Conference on Acoustics, Speech, and Signal Processing, pp. 6316-6320, 44th International Conference on Acoustics, Speech, and Signal Processing, Brighton , United Kingdom, 12/05/19. https://doi.org/10.1109/ICASSP.2019.8682640","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8937069383","display_name":"Safe and secure speech information processing based on liveness detection and ASVspoof challenge","funder_award_id":"18KT0051","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1533861849","https://openalex.org/W1901129140","https://openalex.org/W2123299109","https://openalex.org/W2150769028","https://openalex.org/W2302255633","https://openalex.org/W2340176088","https://openalex.org/W2590129515","https://openalex.org/W2696253854","https://openalex.org/W2747024632","https://openalex.org/W2747872086","https://openalex.org/W2785523195","https://openalex.org/W2785659390","https://openalex.org/W2806569010","https://openalex.org/W2807325376","https://openalex.org/W2807633153","https://openalex.org/W2888828636","https://openalex.org/W2888989492","https://openalex.org/W2888992773","https://openalex.org/W2889084898","https://openalex.org/W2963460857","https://openalex.org/W2963495494","https://openalex.org/W2963800675","https://openalex.org/W2963840672","https://openalex.org/W6631362777","https://openalex.org/W6631943919","https://openalex.org/W6639824700","https://openalex.org/W6696085341","https://openalex.org/W6698183232","https://openalex.org/W6703974891","https://openalex.org/W6747620207","https://openalex.org/W6747831536","https://openalex.org/W6751883949","https://openalex.org/W6753966231"],"related_works":["https://openalex.org/W3007059209","https://openalex.org/W4220832730","https://openalex.org/W1688416049","https://openalex.org/W4312120756","https://openalex.org/W4288120931","https://openalex.org/W4313224733","https://openalex.org/W2972017669","https://openalex.org/W2783658022","https://openalex.org/W2836844603","https://openalex.org/W2585365199"],"abstract_inverted_index":{"An":[0],"attacker":[1],"may":[2],"use":[3],"a":[4,19,95,142],"variety":[5],"of":[6,46,50,78,125],"techniques":[7],"to":[8,26,105],"fool":[9],"an":[10,79,122],"automatic":[11],"speaker":[12],"verification":[13],"system":[14,29,70,135,139],"into":[15],"accepting":[16],"them":[17],"as":[18,54,56],"genuine":[20],"user.":[21],"Anti-spoofing":[22],"methods":[23],"meanwhile":[24],"aim":[25],"make":[27],"the":[28,44,48,89,101,107,128,147],"robust":[30],"against":[31,59],"such":[32],"attacks.":[33],"The":[34],"ASVspoof":[35,129,148],"2017":[36,130,149],"Challenge":[37],"focused":[38],"specifically":[39],"on":[40,127],"replay":[41,51,67],"attacks,":[42],"with":[43],"intention":[45],"measuring":[47],"limits":[49],"attack":[52],"detection":[53,69],"well":[55],"developing":[57],"countermeasures":[58],"them.":[60],"In":[61],"this":[62],"work,":[63],"we":[64],"propose":[65],"our":[66,137],"attacks":[68],"-":[71],"Attentive":[72,118],"Filtering":[73,119],"Network,":[74],"which":[75],"is":[76],"composed":[77],"attention-based":[80],"filtering":[81],"mechanism":[82],"that":[83,100,112],"enhances":[84],"feature":[85,110],"representations":[86,111],"in":[87],"both":[88],"frequency":[90],"and":[91,94],"time":[92],"domains,":[93],"ResNet-based":[96],"classifier.":[97],"We":[98],"show":[99],"network":[102],"enables":[103],"us":[104],"visualize":[106],"automatically":[108],"acquired":[109],"are":[113],"helpful":[114],"for":[115],"spoofing":[116],"detection.":[117],"Network":[120],"attains":[121],"evaluation":[123],"EER":[124],"8.99%":[126],"Version":[131],"2.0":[132],"dataset.":[133],"With":[134],"fusion,":[136],"best":[138],"further":[140],"obtains":[141],"30%":[143],"relative":[144],"improvement":[145],"over":[146],"enhanced":[150],"baseline":[151],"system.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":12}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}