{"id":"https://openalex.org/W2784942369","doi":"https://doi.org/10.1109/isba.2018.8311474","title":"On the use of convolutional neural networks for speech presentation attack detection","display_name":"On the use of convolutional neural networks for speech presentation attack detection","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2784942369","doi":"https://doi.org/10.1109/isba.2018.8311474","mag":"2784942369"},"language":"en","primary_location":{"id":"doi:10.1109/isba.2018.8311474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isba.2018.8311474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 4th International Conference on Identity, Security, and Behavior Analysis (ISBA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/233573","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024538974","display_name":"Pavel Korshunov","orcid":"https://orcid.org/0000-0002-2244-1830"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"P. Korshunov","raw_affiliation_strings":["Idiap, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001741874","display_name":"Andr\u00e9 Gon\u00e7alves","orcid":"https://orcid.org/0000-0002-0320-280X"},"institutions":[{"id":"https://openalex.org/I4210090141","display_name":"Centre for Research and Development in Telecommunications (Brazil)","ror":"https://ror.org/00ej99c12","country_code":"BR","type":"company","lineage":["https://openalex.org/I4210090141"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"A. R. Goncalves","raw_affiliation_strings":["CPqD, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CPqD, Brazil","institution_ids":["https://openalex.org/I4210090141"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068989586","display_name":"Ricardo P. V. Violato","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090141","display_name":"Centre for Research and Development in Telecommunications (Brazil)","ror":"https://ror.org/00ej99c12","country_code":"BR","type":"company","lineage":["https://openalex.org/I4210090141"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"R. P. V. Violato","raw_affiliation_strings":["CPqD, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CPqD, Brazil","institution_ids":["https://openalex.org/I4210090141"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034588685","display_name":"Fl\u00e1vio O. Sim\u00f5es","orcid":"https://orcid.org/0000-0001-5104-1222"},"institutions":[{"id":"https://openalex.org/I4210090141","display_name":"Centre for Research and Development in Telecommunications (Brazil)","ror":"https://ror.org/00ej99c12","country_code":"BR","type":"company","lineage":["https://openalex.org/I4210090141"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"F. O. Simoes","raw_affiliation_strings":["CPqD, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CPqD, Brazil","institution_ids":["https://openalex.org/I4210090141"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016330764","display_name":"S\u00e9bastien Marcel","orcid":"https://orcid.org/0000-0002-2497-9140"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"S. Marcel","raw_affiliation_strings":["Idiap, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8585,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.88742487,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"9","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9986000061035156,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8704683780670166},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.826069712638855},{"id":"https://openalex.org/keywords/spoofing-attack","display_name":"Spoofing attack","score":0.7966927289962769},{"id":"https://openalex.org/keywords/presentation","display_name":"Presentation (obstetrics)","score":0.6427581310272217},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5591832995414734},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5324445962905884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48927780985832214},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4738196134567261},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.47366294264793396},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.43262770771980286},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3654007315635681},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.34721261262893677},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3230181932449341},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1328195333480835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8704683780670166},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.826069712638855},{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.7966927289962769},{"id":"https://openalex.org/C2777601897","wikidata":"https://www.wikidata.org/wiki/Q3409113","display_name":"Presentation (obstetrics)","level":2,"score":0.6427581310272217},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5591832995414734},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5324445962905884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48927780985832214},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4738196134567261},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.47366294264793396},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.43262770771980286},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3654007315635681},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.34721261262893677},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3230181932449341},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1328195333480835},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/isba.2018.8311474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isba.2018.8311474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 4th International Conference on Identity, Security, and Behavior Analysis (ISBA)","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:233573","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/233573","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:233573","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/233573","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1550352777","https://openalex.org/W1638038541","https://openalex.org/W2047346462","https://openalex.org/W2072473772","https://openalex.org/W2083458151","https://openalex.org/W2117544888","https://openalex.org/W2123299109","https://openalex.org/W2148154194","https://openalex.org/W2150008717","https://openalex.org/W2176804518","https://openalex.org/W2295634712","https://openalex.org/W2383245299","https://openalex.org/W2395827581","https://openalex.org/W2402156731","https://openalex.org/W2405506115","https://openalex.org/W2407170210","https://openalex.org/W2533075636","https://openalex.org/W2565961899","https://openalex.org/W2572432338","https://openalex.org/W2576165910","https://openalex.org/W2590129515","https://openalex.org/W2604812030","https://openalex.org/W2738359832","https://openalex.org/W2759701035","https://openalex.org/W4298202768","https://openalex.org/W6640116757","https://openalex.org/W6685748340","https://openalex.org/W6697322189","https://openalex.org/W6712036219","https://openalex.org/W6713239009","https://openalex.org/W6713566751"],"related_works":["https://openalex.org/W2547760228","https://openalex.org/W2836844603","https://openalex.org/W3173366380","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W2144773493"],"abstract_inverted_index":{"Research":[0],"in":[1,20,72,83,87],"the":[2,13,94,117,120,141,145,150,187,199],"area":[3],"of":[4,51,96,106,119,143,147],"automatic":[5],"speaker":[6],"verification":[7],"(ASV)":[8],"has":[9],"advanced":[10],"enough":[11],"for":[12,98],"industry":[14],"to":[15,29,92,164,168,177,190,201,208],"start":[16],"using":[17,110,161],"ASV":[18],"systems":[19,25],"practical":[21],"applications.":[22],"However,":[23,194],"these":[24],"are":[26,53,80,175,206],"highly":[27],"vulnerable":[28],"spoofing":[30],"or":[31,59],"presentation":[32,40,85,131],"attacks(PAs),":[33],"limiting":[34],"their":[35,114],"wide":[36],"deployment.":[37],"Several":[38],"speech-based":[39],"attack":[41],"detection":[42],"(PAD)":[43],"methods":[44],"have":[45,67],"been":[46],"proposed":[47],"recently":[48],"but":[49],"most":[50],"them":[52],"based":[54],"on":[55,126,149,157],"hand":[56,191],"crafted":[57,192],"frequency":[58],"phase-based":[60],"features.":[61,193],"Although":[62],"convolutional":[63],"neural":[64],"networks":[65],"(CNN)":[66],"already":[68],"shown":[69],"breakthrough":[70],"results":[71,171],"face":[73],"recognition,":[74],"little":[75],"is":[76],"understood":[77],"whether":[78],"CNNs":[79,97,148,174],"as":[81],"effective":[82],"detecting":[84],"attacks":[86,211],"speech.":[88],"In":[89],"this":[90],"paper,":[91],"investigate":[93],"applicability":[95],"PAD,":[99],"we":[100],"consider":[101],"shallow":[102],"and":[103,112,136,152,166,205],"deep":[104],"examples":[105],"CNN":[107],"architectures":[108],"implemented":[109],"Tensorflow":[111],"compare":[113],"performances":[115],"with":[116,123,130],"state":[118],"art":[121],"MFCC":[122],"GMM-based":[124],"system":[125],"two":[127],"large":[128],"databases":[129,204],"attacks:":[132],"publicly":[133],"available":[134],"voicePA":[135],"proprietary":[137],"BioCPqD-PA.":[138],"We":[139],"study":[140],"impact":[142],"increasing":[144],"depth":[146,184],"performance,":[151],"note":[153],"how":[154],"they":[155],"perform":[156],"unknown":[158,210],"attacks,":[159],"by":[160],"one":[162],"database":[163,180],"train":[165],"another":[167],"evaluate.":[169],"The":[170],"demonstrate":[172],"that":[173],"able":[176],"learn":[178],"a":[179],"significantly":[181],"better":[182],"(increasing":[183],"also":[185],"improves":[186],"performance),":[188],"compared":[189],"CNN-based":[195],"PADs":[196],"still":[197],"lack":[198],"ability":[200],"generalize":[202],"across":[203],"unable":[207],"detect":[209],"well.":[212]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}