{"id":"https://openalex.org/W4416250577","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227306","title":"Towards Explainable Person-of-Interest-based Audio Synthesis Detection","display_name":"Towards Explainable Person-of-Interest-based Audio Synthesis Detection","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416250577","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227306"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227306","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227306","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5088157699","display_name":"Alessandro Pianese","orcid":"https://orcid.org/0000-0003-4765-8566"},"institutions":[{"id":"https://openalex.org/I71267560","display_name":"University of Naples Federico II","ror":"https://ror.org/05290cv24","country_code":"IT","type":"education","lineage":["https://openalex.org/I71267560"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Pianese","raw_affiliation_strings":["University of Naples Federico II"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Naples Federico II","institution_ids":["https://openalex.org/I71267560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004017099","display_name":"Luca Cuccovillo","orcid":"https://orcid.org/0000-0001-5559-6508"},"institutions":[{"id":"https://openalex.org/I4923324","display_name":"Fraunhofer-Gesellschaft","ror":"https://ror.org/05hkkdn48","country_code":"DE","type":"government","lineage":["https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Luca Cuccovillo","raw_affiliation_strings":["Fraunhofer Institute for Digital Media Technology IDMT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Digital Media Technology IDMT","institution_ids":["https://openalex.org/I4923324"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081981044","display_name":"Giovanni Poggi","orcid":"https://orcid.org/0000-0003-1327-4812"},"institutions":[{"id":"https://openalex.org/I71267560","display_name":"University of Naples Federico II","ror":"https://ror.org/05290cv24","country_code":"IT","type":"education","lineage":["https://openalex.org/I71267560"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giovanni Poggi","raw_affiliation_strings":["University of Naples Federico II"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Naples Federico II","institution_ids":["https://openalex.org/I71267560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102438440","display_name":"Thomas Le Roux","orcid":null},"institutions":[{"id":"https://openalex.org/I4923324","display_name":"Fraunhofer-Gesellschaft","ror":"https://ror.org/05hkkdn48","country_code":"DE","type":"government","lineage":["https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Le Roux","raw_affiliation_strings":["Fraunhofer Institute for Digital Media Technology IDMT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Digital Media Technology IDMT","institution_ids":["https://openalex.org/I4923324"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037565234","display_name":"Patrick Aichroth","orcid":"https://orcid.org/0000-0003-4777-6335"},"institutions":[{"id":"https://openalex.org/I4923324","display_name":"Fraunhofer-Gesellschaft","ror":"https://ror.org/05hkkdn48","country_code":"DE","type":"government","lineage":["https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Patrick Aichroth","raw_affiliation_strings":["Fraunhofer Institute for Digital Media Technology IDMT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Digital Media Technology IDMT","institution_ids":["https://openalex.org/I4923324"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.4636000096797943,"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":0.4636000096797943,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.12319999933242798,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.09480000287294388,"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/generalization","display_name":"Generalization","score":0.7027000188827515},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5390999913215637},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.521399974822998},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5206999778747559},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.45179998874664307},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.38420000672340393},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.37950000166893005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.803600013256073},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7027000188827515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5946000218391418},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5390999913215637},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.521399974822998},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5206999778747559},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47679999470710754},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.45179998874664307},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40799999237060547},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.38420000672340393},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.37950000166893005},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.3488999903202057},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31869998574256897},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3021000027656555},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.27639999985694885},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.267300009727478}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227306","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227306","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/503263","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/503263","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310077","display_name":"National Research Centre","ror":"https://ror.org/02n85j827"},{"id":"https://openalex.org/F4320311687","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2120847449","https://openalex.org/W2152859600","https://openalex.org/W2555915854","https://openalex.org/W2590129515","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2969985801","https://openalex.org/W3024869864","https://openalex.org/W3026777299","https://openalex.org/W3127781933","https://openalex.org/W3157576687","https://openalex.org/W3163596559","https://openalex.org/W3200167423","https://openalex.org/W3201773091","https://openalex.org/W4297841787","https://openalex.org/W4299806750","https://openalex.org/W4311737082","https://openalex.org/W4312743281","https://openalex.org/W4385823264","https://openalex.org/W4385975857","https://openalex.org/W4386432956","https://openalex.org/W4388117344","https://openalex.org/W4390481409","https://openalex.org/W4391021719","https://openalex.org/W4392909950","https://openalex.org/W4396785992","https://openalex.org/W4402915903","https://openalex.org/W4403182579","https://openalex.org/W4406345321","https://openalex.org/W4406521093"],"related_works":[],"abstract_inverted_index":{"Generalization":[0],"and":[1,32,94,119],"explainability":[2],"are":[3],"two":[4],"key":[5],"challenges":[6],"in":[7],"synthetic":[8,57],"audio":[9,58,71],"detection.":[10],"Effective":[11],"detectors":[12],"should":[13],"not":[14],"only":[15,63],"reliably":[16],"classify":[17],"unseen":[18],"data":[19],"from":[20],"unknown":[21],"synthesis":[22],"algorithms,":[23],"but":[24],"also":[25],"provide":[26],"insight":[27],"into":[28],"their":[29],"decision-making":[30],"process":[31],"explain":[33],"why":[34],"a":[35,60],"given":[36],"input":[37],"was":[38],"classified":[39],"as":[40,100,102],"real":[41,65],"or":[42],"fake.":[43],"To":[44,78],"promote":[45],"generalization":[46],"we":[47,81],"use":[48,83],"the":[49,73,89,98],"Person-of-Interest":[50],"approach,":[51],"which":[52],"allows":[53],"us":[54],"to":[55,97],"detect":[56],"using":[59],"model":[61],"trained":[62],"on":[64,116,122],"data,":[66],"provided":[67],"that":[68,88,108],"some":[69],"pristine":[70],"of":[72],"putative":[74],"speaker":[75,123],"is":[76],"provided.":[77],"support":[79],"explainability,":[80],"instead":[82],"an":[84],"encoder-decoder":[85],"backbone":[86],"such":[87],"bottleneck":[90],"features":[91],"ensure":[92],"syntactic":[93],"semantic":[95],"fidelity":[96],"input,":[99],"well":[101],"enable":[103],"reliable":[104],"decisions.":[105],"Experiments":[106],"show":[107],"our":[109],"approach":[110],"outperforms":[111],"both":[112],"state-of-the-art":[113],"models":[114],"based":[115,121],"supervised":[117],"learning":[118],"methods":[120],"verification.":[124]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}