{"id":"https://openalex.org/W4404239174","doi":"https://doi.org/10.1109/ijcb62174.2024.10744479","title":"Context Encoded Multi-Modal Attention Network for Detecting Audio Spoofing","display_name":"Context Encoded Multi-Modal Attention Network for Detecting Audio Spoofing","publication_year":2024,"publication_date":"2024-09-15","ids":{"openalex":"https://openalex.org/W4404239174","doi":"https://doi.org/10.1109/ijcb62174.2024.10744479"},"language":"en","primary_location":{"id":"doi:10.1109/ijcb62174.2024.10744479","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcb62174.2024.10744479","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Joint Conference on Biometrics (IJCB)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5110852852","display_name":"Rishabh Ranjan","orcid":null},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rishabh Ranjan","raw_affiliation_strings":["Indian Institute of Technology, Jodhpur,Jodhpur,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Jodhpur,Jodhpur,India","institution_ids":["https://openalex.org/I154549908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050521702","display_name":"Mayank Vatsa","orcid":"https://orcid.org/0000-0001-5952-2274"},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mayank Vatsa","raw_affiliation_strings":["Indian Institute of Technology, Jodhpur,Jodhpur,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Jodhpur,Jodhpur,India","institution_ids":["https://openalex.org/I154549908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011779957","display_name":"Richa Singh","orcid":"https://orcid.org/0000-0003-4060-4573"},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Richa Singh","raw_affiliation_strings":["Indian Institute of Technology, Jodhpur,Jodhpur,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Jodhpur,Jodhpur,India","institution_ids":["https://openalex.org/I154549908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154549908"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9919000267982483,"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/T10860","display_name":"Speech and Audio Processing","score":0.9919000267982483,"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/T11309","display_name":"Music and Audio Processing","score":0.9907000064849854,"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":0.9898999929428101,"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":0.7616926431655884},{"id":"https://openalex.org/keywords/spoofing-attack","display_name":"Spoofing attack","score":0.7484785318374634},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5731857419013977},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5309357643127441},{"id":"https://openalex.org/keywords/digital-audio-broadcasting","display_name":"Digital audio broadcasting","score":0.42457765340805054},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.42261797189712524},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3897678852081299},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.339446485042572},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.2239667773246765},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.20043081045150757},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.19886642694473267}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7616926431655884},{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.7484785318374634},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5731857419013977},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5309357643127441},{"id":"https://openalex.org/C2779106878","wikidata":"https://www.wikidata.org/wiki/Q1257510","display_name":"Digital audio broadcasting","level":2,"score":0.42457765340805054},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.42261797189712524},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3897678852081299},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.339446485042572},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.2239667773246765},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.20043081045150757},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.19886642694473267},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcb62174.2024.10744479","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcb62174.2024.10744479","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Joint Conference on Biometrics (IJCB)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W2105482032","https://openalex.org/W2114925438","https://openalex.org/W2176804518","https://openalex.org/W2295634712","https://openalex.org/W2383245299","https://openalex.org/W2394783243","https://openalex.org/W2403139431","https://openalex.org/W2584505851","https://openalex.org/W2745896134","https://openalex.org/W2747329762","https://openalex.org/W2763881998","https://openalex.org/W2799053639","https://openalex.org/W2936802426","https://openalex.org/W2962959915","https://openalex.org/W2963508548","https://openalex.org/W2964052309","https://openalex.org/W2967606780","https://openalex.org/W2989571531","https://openalex.org/W3007151378","https://openalex.org/W3024920698","https://openalex.org/W3026777299","https://openalex.org/W3093400813","https://openalex.org/W3096084197","https://openalex.org/W3096109555","https://openalex.org/W3127781933","https://openalex.org/W3158663310","https://openalex.org/W3160325739","https://openalex.org/W3161011913","https://openalex.org/W3163596559","https://openalex.org/W3168707441","https://openalex.org/W3175036090","https://openalex.org/W3196368020","https://openalex.org/W3197134965","https://openalex.org/W3197358873","https://openalex.org/W3198329097","https://openalex.org/W3200167423","https://openalex.org/W3201773091","https://openalex.org/W3212117663","https://openalex.org/W4297841787","https://openalex.org/W4317181815","https://openalex.org/W4360992936","https://openalex.org/W4367046815","https://openalex.org/W4392411893","https://openalex.org/W4394671563","https://openalex.org/W6780218876","https://openalex.org/W6789403026","https://openalex.org/W6790356757","https://openalex.org/W6854698059"],"related_works":["https://openalex.org/W2188559950","https://openalex.org/W2989910292","https://openalex.org/W2998478967","https://openalex.org/W2130109774","https://openalex.org/W1502144745","https://openalex.org/W1979717040","https://openalex.org/W2085199577","https://openalex.org/W4254454621","https://openalex.org/W2276003394","https://openalex.org/W2560649957"],"abstract_inverted_index":{"Humans":[0],"interpret":[1],"speech":[2,17],"through":[3,48],"both":[4],"acoustic":[5],"and":[6,60,74],"textual":[7,99],"signals.":[8],"Recognizing":[9],"the":[10,49,85,96,106],"importance":[11],"of":[12,51,98],"incorporating":[13],"contextual":[14],"information":[15],"into":[16],"processing,":[18],"especially":[19],"for":[20,77],"spoofing":[21,124],"detection,":[22],"we":[23],"introduce":[24],"a":[25,52],"multimodal":[26,54,67],"representation":[27],"framework":[28,87],"that":[29,70,95],"integrates":[30],"text":[31,73],"with":[32],"audio":[33,75,123],"signals":[34],"to":[35],"enhance":[36],"spoof":[37,55,115],"detection":[38,56,79,116],"effectiveness.":[39],"This":[40],"research":[41],"advances":[42],"in":[43,91,118],"two":[44],"significant":[45],"ways:":[46],"firstly,":[47],"creation":[50],"new":[53],"model":[57,103,108],"called":[58],"Raw-BERT,":[59],"secondly,":[61],"by":[62],"developing":[63],"an":[64],"innovative":[65],"multi-headed":[66],"attention":[68],"network":[69],"synergistically":[71],"merges":[72],"data":[76],"enhanced":[78],"capabilities.":[80],"We":[81],"have":[82],"extensively":[83],"evaluated":[84],"proposed":[86,107],"across":[88],"diverse":[89],"datasets":[90],"various":[92],"languages,":[93],"demonstrating":[94],"addition":[97],"context":[100],"significantly":[101],"boosts":[102],"performance.":[104],"Overall,":[105],"demonstrates":[109],"superior":[110],"results,":[111],"consistently":[112],"outperforming":[113],"existing":[114],"algorithms":[117],"multiple":[119],"evaluations":[120],"on":[121],"benchmark":[122],"datasets.":[125]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
