{"id":"https://openalex.org/W4399261702","doi":"https://doi.org/10.1145/3643491.3660288","title":"Audio Transformer for Synthetic Speech Detection via Benford's Law Distribution Analysis","display_name":"Audio Transformer for Synthetic Speech Detection via Benford's Law Distribution Analysis","publication_year":2024,"publication_date":"2024-06-01","ids":{"openalex":"https://openalex.org/W4399261702","doi":"https://doi.org/10.1145/3643491.3660288"},"language":"en","primary_location":{"id":"doi:10.1145/3643491.3660288","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3643491.3660288","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"3rd ACM International Workshop on Multimedia AI against Disinformation","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3643491.3660288","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5098974795","display_name":"Anitha Bhat Talagini Ashoka","orcid":"https://orcid.org/0009-0007-7717-6943"},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Anitha Bhat Talagini Ashoka","raw_affiliation_strings":["Fraunhofer Institute for Digital Media Technology IDMT, Germany"],"raw_orcid":"https://orcid.org/0009-0007-7717-6943","affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Digital Media Technology IDMT, Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"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/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Luca Cuccovillo","raw_affiliation_strings":["Fraunhofer Institute for Digital Media Technology IDMT\\t, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5559-6508","affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Digital Media Technology IDMT\\t, Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"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/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Patrick Aichroth","raw_affiliation_strings":["Fraunhofer Institute for Digital Media Technology IDMT\\t, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4777-6335","affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Digital Media Technology IDMT\\t, Germany","institution_ids":["https://openalex.org/I4210138578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210138578"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9965999722480774,"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":0.9726999998092651,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benfords-law","display_name":"Benford's law","score":0.9308974742889404},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.8093222379684448},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6848013401031494},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6466729044914246},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5681668519973755},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5433796644210815},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5412471294403076},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4259503185749054},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3822038173675537},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3784920871257782},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3276956379413605},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1475863754749298},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1078050434589386},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09634971618652344}],"concepts":[{"id":"https://openalex.org/C152636012","wikidata":"https://www.wikidata.org/wiki/Q817168","display_name":"Benford's law","level":2,"score":0.9308974742889404},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8093222379684448},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6848013401031494},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6466729044914246},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5681668519973755},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5433796644210815},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5412471294403076},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4259503185749054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3822038173675537},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3784920871257782},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3276956379413605},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1475863754749298},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1078050434589386},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09634971618652344},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3643491.3660288","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3643491.3660288","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"3rd ACM International Workshop on Multimedia AI against Disinformation","raw_type":"proceedings-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/472890","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/472890","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":{"id":"doi:10.1145/3643491.3660288","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3643491.3660288","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"3rd ACM International Workshop on Multimedia AI against Disinformation","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1282871347","display_name":null,"funder_award_id":"101070093","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W1519689712","https://openalex.org/W2001826293","https://openalex.org/W2045254357","https://openalex.org/W2056716515","https://openalex.org/W2060626867","https://openalex.org/W2194775991","https://openalex.org/W2615063356","https://openalex.org/W2742330194","https://openalex.org/W2962858109","https://openalex.org/W3026777299","https://openalex.org/W3163596559","https://openalex.org/W3200167423","https://openalex.org/W3200527256","https://openalex.org/W4311591823"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W642007152","https://openalex.org/W4253660971","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W1909292483","https://openalex.org/W2052688117","https://openalex.org/W2550171623","https://openalex.org/W596245619"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,34],"novel":[4],"approach":[5,46],"that":[6],"enhances":[7],"synthetic":[8],"speech":[9],"detection":[10],"by":[11],"applying":[12],"Benford\u2019s":[13,22],"law":[14],"analysis":[15],"to":[16],"the":[17,28,31,51],"encoder":[18],"embeddings.":[19],"By":[20],"leveraging":[21],"Law":[23],"as":[24],"supplementary":[25],"information":[26],"alongside":[27],"existing":[29],"embeddings,":[30],"model":[32],"gains":[33],"detailed":[35],"understanding":[36],"of":[37,60],"both":[38],"content-related":[39],"features":[40],"and":[41],"numerical":[42],"distribution":[43],"patterns.":[44],"Our":[45],"demonstrates":[47],"superior":[48],"performance":[49],"on":[50],"ASVspoof":[52],"2019":[53],"LA":[54],"dataset,":[55],"achieving":[56],"an":[57],"AUC":[58],"score":[59],"0.921,":[61],"while":[62],"providing":[63],"enhanced":[64],"interpretability.":[65]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2024-06-02T00:00:00"}
