{"id":"https://openalex.org/W4414170769","doi":"https://doi.org/10.1109/avss65446.2025.11149956","title":"XLSR-Kanformer: A KAN-Intergrated model for Synthetic Speech Detection","display_name":"XLSR-Kanformer: A KAN-Intergrated model for Synthetic Speech Detection","publication_year":2025,"publication_date":"2025-08-11","ids":{"openalex":"https://openalex.org/W4414170769","doi":"https://doi.org/10.1109/avss65446.2025.11149956"},"language":"en","primary_location":{"id":"doi:10.1109/avss65446.2025.11149956","is_oa":false,"landing_page_url":"https://doi.org/10.1109/avss65446.2025.11149956","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Advanced Visual and Signal-Based Systems (AVSS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.06706","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114218708","display_name":"Phuong Tuan Dat","orcid":null},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Phuong Tuan Dat","raw_affiliation_strings":["Hanoi University of Science and Technology,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology,Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110125670","display_name":"Tran Huy Dat","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tran Huy Dat","raw_affiliation_strings":["A*STAR,Institute for Infocomm Research (I2R),Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"A*STAR,Institute for Infocomm Research (I2R),Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.998199999332428,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9896000027656555,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5142999887466431},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4681999981403351},{"id":"https://openalex.org/keywords/spoofing-attack","display_name":"Spoofing attack","score":0.45809999108314514},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4577000141143799},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.45170000195503235},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4255000054836273},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.41620001196861267},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.41290000081062317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7504000067710876},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6754999756813049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5171999931335449},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5142999887466431},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4681999981403351},{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.45809999108314514},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4577000141143799},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.45170000195503235},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4255000054836273},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.41620001196861267},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.41290000081062317},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3815999925136566},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32510000467300415},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.3012000024318695},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2799000144004822},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.27790001034736633},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.275299996137619}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/avss65446.2025.11149956","is_oa":false,"landing_page_url":"https://doi.org/10.1109/avss65446.2025.11149956","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Advanced Visual and Signal-Based Systems (AVSS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.06706","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.06706","pdf_url":"https://arxiv.org/pdf/2510.06706","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.06706","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.06706","pdf_url":"https://arxiv.org/pdf/2510.06706","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4414170769.pdf"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2137983211","https://openalex.org/W2890964092","https://openalex.org/W2936802426","https://openalex.org/W2967606780","https://openalex.org/W3035390927","https://openalex.org/W3036601975","https://openalex.org/W3097777922","https://openalex.org/W3127995079","https://openalex.org/W3163596559","https://openalex.org/W3201773091","https://openalex.org/W3202370288","https://openalex.org/W3211424380","https://openalex.org/W3213029956","https://openalex.org/W4221154745","https://openalex.org/W4225527248","https://openalex.org/W4375869126","https://openalex.org/W4381198892","https://openalex.org/W4385822395","https://openalex.org/W4396821501","https://openalex.org/W4396944743","https://openalex.org/W4399912438","https://openalex.org/W4402111996"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,37,62,102,145],"speech":[3,39,147],"synthesis":[4],"technologies":[5],"have":[6,33],"led":[7],"to":[8,92,126],"increasingly":[9],"sophisticated":[10],"spoofing":[11],"attacks,":[12],"posing":[13],"significant":[14],"challenges":[15],"for":[16,44,143],"automatic":[17],"speaker":[18],"verification":[19],"systems.":[20],"While":[21],"systems":[22],"based":[23,75],"on":[24,76,84,115],"self-supervised":[25],"learning":[26],"(SSL)":[27],"models,":[28],"particularly":[29],"the":[30,57,63,77,88,97,116,120],"XLSR-Conformer":[31,64,93],"architecture,":[32],"demonstrated":[34],"remarkable":[35],"performance":[36,98],"synthetic":[38,146],"detection,":[40],"there":[41],"remains":[42],"room":[43],"architectural":[45],"improvements.":[46],"In":[47],"this":[48],"paper,":[49],"we":[50],"propose":[51],"a":[52,67,71,140],"novel":[53],"approach":[54],"that":[55,87,133],"replaces":[56],"traditional":[58],"Multi-Layer":[59],"Perceptron":[60],"(MLP)":[61],"model":[65,94],"with":[66],"Kolmogorov-Arnold":[68,78],"Network":[69],"(KAN),":[70],"powerful":[72],"universal":[73],"approximator":[74],"representation":[79],"theorem.":[80],"Our":[81],"experimental":[82],"results":[83],"ASVspoof2021":[85],"demonstrate":[86],"integration":[89],"of":[90],"KAN":[91,135],"can":[95],"improve":[96],"by":[99],"60.55%":[100],"relatively":[101],"Equal":[103],"Error":[104],"Rate":[105],"(EER)":[106],"LA":[107],"and":[108],"DF":[109],"sets,":[110],"further":[111],"achieving":[112],"0.70%":[113],"EER":[114],"21LA":[117],"set.":[118],"Besides,":[119],"proposed":[121],"replacement":[122],"is":[123,139],"also":[124],"robust":[125],"various":[127],"SSL":[128],"architectures.":[129],"These":[130],"findings":[131],"suggest":[132],"incorporating":[134],"into":[136],"SSL-based":[137],"models":[138],"promising":[141],"direction":[142],"advances":[144],"detection.":[148]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}