{"id":"https://openalex.org/W4385823108","doi":"https://doi.org/10.21437/interspeech.2023-245","title":"Towards Attention-based Contrastive Learning for Audio Spoof Detection","display_name":"Towards Attention-based Contrastive Learning for Audio Spoof Detection","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823108","doi":"https://doi.org/10.21437/interspeech.2023-245"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-245","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-245","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2407.03514","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037890749","display_name":"Chirag Goel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119400","display_name":"Division of Public Defender Services","ror":"https://ror.org/02sksqx64","country_code":"US","type":"government","lineage":["https://openalex.org/I4210119400"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chirag Goel","raw_affiliation_strings":["Reality Defender Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reality Defender Inc., USA","institution_ids":["https://openalex.org/I4210119400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092639627","display_name":"Surya Koppisetti","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119400","display_name":"Division of Public Defender Services","ror":"https://ror.org/02sksqx64","country_code":"US","type":"government","lineage":["https://openalex.org/I4210119400"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Surya Koppisetti","raw_affiliation_strings":["Reality Defender Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reality Defender Inc., USA","institution_ids":["https://openalex.org/I4210119400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092639628","display_name":"Ben Colman","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119400","display_name":"Division of Public Defender Services","ror":"https://ror.org/02sksqx64","country_code":"US","type":"government","lineage":["https://openalex.org/I4210119400"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ben Colman","raw_affiliation_strings":["Reality Defender Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reality Defender Inc., USA","institution_ids":["https://openalex.org/I4210119400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109491559","display_name":"Ali Shahriyari","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119400","display_name":"Division of Public Defender Services","ror":"https://ror.org/02sksqx64","country_code":"US","type":"government","lineage":["https://openalex.org/I4210119400"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Shahriyari","raw_affiliation_strings":["Reality Defender Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reality Defender Inc., USA","institution_ids":["https://openalex.org/I4210119400"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036255713","display_name":"Gaurav Bharaj","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119400","display_name":"Division of Public Defender Services","ror":"https://ror.org/02sksqx64","country_code":"US","type":"government","lineage":["https://openalex.org/I4210119400"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gaurav Bharaj","raw_affiliation_strings":["Reality Defender Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reality Defender Inc., USA","institution_ids":["https://openalex.org/I4210119400"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210119400"],"apc_list":null,"apc_paid":null,"fwci":1.2779,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.80757566,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2758","last_page":"2762"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":0.9997000098228455,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8376421928405762},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6115717887878418},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5560749769210815},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.550987958908081},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.5250199437141418},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.48833581805229187},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45942381024360657},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4445638358592987},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4381427764892578},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.42716801166534424},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42060354351997375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8376421928405762},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6115717887878418},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5560749769210815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.550987958908081},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.5250199437141418},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.48833581805229187},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45942381024360657},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4445638358592987},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4381427764892578},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.42716801166534424},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42060354351997375},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2023-245","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-245","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2407.03514","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.03514","pdf_url":"https://arxiv.org/pdf/2407.03514","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2407.03514","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.03514","pdf_url":"https://arxiv.org/pdf/2407.03514","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385823108.pdf","grobid_xml":"https://content.openalex.org/works/W4385823108.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2295634712","https://openalex.org/W2590129515","https://openalex.org/W2593116425","https://openalex.org/W2747664154","https://openalex.org/W2903739847","https://openalex.org/W2963077989","https://openalex.org/W2963138647","https://openalex.org/W2964227577","https://openalex.org/W2972811785","https://openalex.org/W3005680577","https://openalex.org/W3036601975","https://openalex.org/W3081492798","https://openalex.org/W3091905774","https://openalex.org/W3094502228","https://openalex.org/W3131786367","https://openalex.org/W3144810982","https://openalex.org/W3151130473","https://openalex.org/W3162391496","https://openalex.org/W3163596559","https://openalex.org/W3171442995","https://openalex.org/W3196837826","https://openalex.org/W3196974791","https://openalex.org/W3197358873","https://openalex.org/W3198529186","https://openalex.org/W3201397251","https://openalex.org/W3201612248","https://openalex.org/W3206996142","https://openalex.org/W3207579445","https://openalex.org/W4225527248","https://openalex.org/W4225607460","https://openalex.org/W4225854381","https://openalex.org/W4283320581","https://openalex.org/W4287325149","https://openalex.org/W4287372095","https://openalex.org/W4287812705","https://openalex.org/W4291331874","https://openalex.org/W4295308583","https://openalex.org/W4381198892"],"related_works":["https://openalex.org/W2948333011","https://openalex.org/W4386619269","https://openalex.org/W1942758450","https://openalex.org/W2994972936","https://openalex.org/W2922338626","https://openalex.org/W4303645333","https://openalex.org/W4312745891","https://openalex.org/W3088045114","https://openalex.org/W2108010283","https://openalex.org/W4221067497"],"abstract_inverted_index":{"Vision":[0],"transformers":[1],"(ViT)":[2],"have":[3],"made":[4],"substantial":[5],"progress":[6],"for":[7,21,34,46,107],"classification":[8],"tasks":[9],"in":[10],"computer":[11],"vision.":[12],"Recently,":[13],"Gong":[14],"et.":[15,58],"al.":[16,59],"'21,":[17],"introduced":[18],"attention-based":[19,77],"modeling":[20],"several":[22],"audio":[23,35,61],"tasks.":[24],"However,":[25],"relatively":[26],"unexplored":[27],"is":[28],"the":[29,55,87,97,108,125],"use":[30],"of":[31],"a":[32,75,115],"ViT":[33,62],"spoof":[36,100],"detection":[37],"task.":[38,48,109],"We":[39,129],"bridge":[40],"this":[41,47],"gap":[42],"and":[43,99,102,132],"introduce":[44],"ViTs":[45],"A":[49],"vanilla":[50],"baseline":[51],"built":[52],"on":[53,118,124],"fine-tuning":[54],"SSAST":[56],"(Gong":[57],"'22)":[60],"model":[63,116],"achieves":[64,121],"sub-optimal":[65],"equal":[66],"error":[67],"rates":[68],"(EERs).":[69],"To":[70],"improve":[71],"performance,":[72],"we":[73],"propose":[74],"novel":[76],"contrastive":[78],"learning":[79],"framework":[80,94,120],"(SSAST-CL)":[81],"that":[82,92],"uses":[83],"cross-attention":[84],"to":[85,135],"aid":[86],"representation":[88],"learning.":[89],"Experiments":[90],"show":[91],"our":[93,119,137],"successfully":[95],"disentangles":[96],"bonafide":[98],"classes":[101],"helps":[103],"learn":[104],"better":[105],"classifiers":[106],"With":[110],"appropriate":[111],"data":[112],"augmentations":[113],"policy,":[114],"trained":[117],"competitive":[122],"performance":[123],"ASVSpoof":[126],"2021":[127],"challenge.":[128],"provide":[130],"comparisons":[131],"ablation":[133],"studies":[134],"justify":[136],"claim.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}