{"id":"https://openalex.org/W3160325739","doi":"https://doi.org/10.1109/icassp39728.2021.9414670","title":"A Capsule Network Based Approach for Detection of Audio Spoofing Attacks","display_name":"A Capsule Network Based Approach for Detection of Audio Spoofing Attacks","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160325739","doi":"https://doi.org/10.1109/icassp39728.2021.9414670","mag":"3160325739"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5042582166","display_name":"Anwei Luo","orcid":"https://orcid.org/0009-0004-7071-9886"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Anwei Luo","raw_affiliation_strings":["Key Lab of Information Security, School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Lab of Information Security, School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077750442","display_name":"Enlei Li","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enlei Li","raw_affiliation_strings":["Key Lab of Information Security, School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Lab of Information Security, School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100602207","display_name":"Yongliang Liu","orcid":"https://orcid.org/0000-0002-0320-4426"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongliang Liu","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077333494","display_name":"Xiangui Kang","orcid":"https://orcid.org/0000-0002-3134-0353"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangui Kang","raw_affiliation_strings":["Key Lab of Information Security, School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Lab of Information Security, School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051587486","display_name":"Z. Jane Wang","orcid":"https://orcid.org/0000-0002-3791-0249"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Z. Jane Wang","raw_affiliation_strings":["University of British Columbia, Vancouver, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of British Columbia, Vancouver, Canada","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.5154,"has_fulltext":false,"cited_by_count":80,"citation_normalized_percentile":{"value":0.98356339,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6359","last_page":"6363"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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/spoofing-attack","display_name":"Spoofing attack","score":0.9102966785430908},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8483498692512512},{"id":"https://openalex.org/keywords/replay-attack","display_name":"Replay attack","score":0.7430769801139832},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6454591155052185},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6229477524757385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41199153661727905},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4031234383583069},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.36464300751686096},{"id":"https://openalex.org/keywords/authentication","display_name":"Authentication (law)","score":0.07655447721481323}],"concepts":[{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.9102966785430908},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8483498692512512},{"id":"https://openalex.org/C11560541","wikidata":"https://www.wikidata.org/wiki/Q1756025","display_name":"Replay attack","level":3,"score":0.7430769801139832},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6454591155052185},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6229477524757385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41199153661727905},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4031234383583069},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.36464300751686096},{"id":"https://openalex.org/C148417208","wikidata":"https://www.wikidata.org/wiki/Q4825882","display_name":"Authentication (law)","level":2,"score":0.07655447721481323},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","score":0.5099999904632568,"display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2966661","https://openalex.org/W1522301498","https://openalex.org/W2212624298","https://openalex.org/W2302255633","https://openalex.org/W2531409750","https://openalex.org/W2565961899","https://openalex.org/W2782422271","https://openalex.org/W2785994986","https://openalex.org/W2808125772","https://openalex.org/W2810350850","https://openalex.org/W2901997113","https://openalex.org/W2936802426","https://openalex.org/W2962924597","https://openalex.org/W2963703618","https://openalex.org/W2963720850","https://openalex.org/W2964121744","https://openalex.org/W2967606780","https://openalex.org/W2970759645","https://openalex.org/W2972786657","https://openalex.org/W2972811785","https://openalex.org/W2973181078","https://openalex.org/W3015774894","https://openalex.org/W3016138785","https://openalex.org/W3033711348","https://openalex.org/W3110369781","https://openalex.org/W6631190155","https://openalex.org/W6698183232","https://openalex.org/W6743446608","https://openalex.org/W6748053814","https://openalex.org/W6748181857","https://openalex.org/W6756197946","https://openalex.org/W6780910827"],"related_works":["https://openalex.org/W2610549918","https://openalex.org/W2763821861","https://openalex.org/W3017138616","https://openalex.org/W1993138332","https://openalex.org/W3177248053","https://openalex.org/W2982457063","https://openalex.org/W2954943288","https://openalex.org/W4240391529","https://openalex.org/W1555977059","https://openalex.org/W3097731564"],"abstract_inverted_index":{"Audio":[0],"spoofing":[1],"attacks":[2],"not":[3],"only":[4],"increasingly":[5],"pose":[6],"a":[7,70],"threat":[8],"to":[9,19,37,57,73,97,101,105],"automatic":[10],"speaker":[11],"verification":[12],"systems":[13],"but":[14],"also":[15,122,133],"have":[16],"the":[17,58,65,75,78,83,92,99,125],"potential":[18],"destabilize":[20],"national":[21],"security":[22],"(e.g.,":[23],"by":[24,42],"creating":[25],"fake":[26,39],"audio":[27],"of":[28,34,77,136],"influential":[29],"politicians).":[30],"The":[31],"main":[32],"purpose":[33],"anti-spoofing":[35,88],"is":[36,121,132],"detect":[38],"audios":[40],"synthesized":[41],"advanced":[43],"methods,":[44],"while":[45],"current":[46],"algorithms":[47],"using":[48],"convolutional":[49],"neural":[50],"networks":[51],"as":[52,64],"classifiers":[53],"exposed":[54],"poor":[55],"generalization":[56,76],"unknown":[59],"attacks.":[60,116,139],"In":[61],"this":[62],"paper,":[63],"first":[66],"attempt,":[67],"we":[68,90],"introduce":[69],"capsule":[71,84],"network":[72,85],"enhance":[74],"detection":[79,111,120],"system.":[80],"To":[81],"make":[82],"suitable":[86],"for":[87,113],"tasks,":[89],"modified":[91],"original":[93],"dynamic":[94],"routing":[95],"algorithm":[96],"force":[98],"model":[100],"pay":[102],"more":[103],"attention":[104],"artifacts":[106],"and":[107,124],"thus":[108],"yield":[109],"better":[110],"performance":[112],"text-to-speech/voice":[114],"conversion":[115],"Furthermore,":[117],"replay":[118,138],"attack":[119],"investigated,":[123],"results":[126],"indicate":[127],"that":[128],"our":[129],"proposed":[130],"approach":[131],"highly":[134],"capable":[135],"detecting":[137]},"counts_by_year":[{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
