{"id":"https://openalex.org/W4392904557","doi":"https://doi.org/10.1109/icassp48485.2024.10445932","title":"Audio Transformer for Synthetic Speech Detection via Formant Magnitude and Phase Analysis","display_name":"Audio Transformer for Synthetic Speech Detection via Formant Magnitude and Phase Analysis","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904557","doi":"https://doi.org/10.1109/icassp48485.2024.10445932"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445932","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/communities/veraai","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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,Ilmenau,Germany,98693"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Digital Media Technology IDMT,Ilmenau,Germany,98693","institution_ids":["https://openalex.org/I4210138578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023780827","display_name":"Milica Gerhardt","orcid":"https://orcid.org/0000-0003-0017-9656"},"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":"Milica Gerhardt","raw_affiliation_strings":["Fraunhofer Institute for Digital Media Technology IDMT,Ilmenau,Germany,98693"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Digital Media Technology IDMT,Ilmenau,Germany,98693","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,Ilmenau,Germany,98693"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Digital Media Technology IDMT,Ilmenau,Germany,98693","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":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4805","last_page":"4809"},"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":0.9998999834060669,"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":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.7354112267494202},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7020552754402161},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6789789199829102},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.6586722135543823},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5950345993041992},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5130358934402466},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.4928012192249298},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.47593024373054504},{"id":"https://openalex.org/keywords/magnitude","display_name":"Magnitude (astronomy)","score":0.4480017125606537},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.422643780708313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3725685179233551},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33199626207351685},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11319524049758911},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.11166176199913025}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7354112267494202},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7020552754402161},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6789789199829102},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.6586722135543823},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5950345993041992},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5130358934402466},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.4928012192249298},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.47593024373054504},{"id":"https://openalex.org/C126691448","wikidata":"https://www.wikidata.org/wiki/Q2028919","display_name":"Magnitude (astronomy)","level":2,"score":0.4480017125606537},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.422643780708313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3725685179233551},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33199626207351685},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11319524049758911},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.11166176199913025},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445932","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/467719","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/467719","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"},{"id":"pmh:oai:zenodo.org:10514309","is_oa":true,"landing_page_url":"https://zenodo.org/communities/veraai","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing, Seoul, Korea, 2024","raw_type":"info:eu-repo/semantics/conferencePaper"},{"id":"doi:10.5281/zenodo.10514309","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10514309","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:10514309","is_oa":true,"landing_page_url":"https://zenodo.org/communities/veraai","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing, Seoul, Korea, 2024","raw_type":"info:eu-repo/semantics/conferencePaper"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2151224667","display_name":"vera.ai: VERification Assisted by Artificial Intelligence","funder_award_id":"101070093","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"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":21,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W2936802426","https://openalex.org/W2962858109","https://openalex.org/W2967606780","https://openalex.org/W3026777299","https://openalex.org/W3160325739","https://openalex.org/W3160747466","https://openalex.org/W3163596559","https://openalex.org/W3186285959","https://openalex.org/W3200167423","https://openalex.org/W3200527256","https://openalex.org/W4283448715","https://openalex.org/W4293363567","https://openalex.org/W4297841787","https://openalex.org/W4311591887","https://openalex.org/W4311740777","https://openalex.org/W4385245566","https://openalex.org/W4388117344","https://openalex.org/W4390481409","https://openalex.org/W6726497184","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W2025848302","https://openalex.org/W1975454382","https://openalex.org/W2799441357","https://openalex.org/W5449343","https://openalex.org/W2409530148","https://openalex.org/W2053642297","https://openalex.org/W4250508028","https://openalex.org/W4403337003","https://openalex.org/W2070513494","https://openalex.org/W596245619"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,22],"novel":[4],"multi-task":[5],"transformer":[6],"for":[7],"synthetic":[8,48],"speech":[9,20,46],"detection.":[10],"The":[11,51],"network":[12],"encodes":[13],"magnitude":[14],"and":[15,40],"phase":[16],"of":[17,35,70],"the":[18,28,33,36,44,57],"input":[19,29,45],"with":[21,66],"feature":[23],"bottleneck,":[24],"used":[25],"to":[26,31,41],"autoencode":[27],"magnitude,":[30],"predict":[32],"trajectory":[34],"fundamental":[37],"frequency":[38],"(f0),":[39],"discern":[42],"if":[43],"is":[47],"or":[49],"natural.":[50],"approach":[52],"achieves":[53],"state-of-the-art":[54],"performance":[55],"on":[56],"ASVspoof":[58],"2019":[59],"LA":[60],"dataset":[61],"while":[62],"still":[63],"retaining":[64],"interpretability,":[65],"an":[67],"AUC":[68],"score":[69],"0.910.":[71]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
