{"id":"https://openalex.org/W4390481409","doi":"https://doi.org/10.1109/wifs58808.2023.10374615","title":"Audio Spectrogram Transformer for Synthetic Speech Detection via Speech Formant Analysis","display_name":"Audio Spectrogram Transformer for Synthetic Speech Detection via Speech Formant Analysis","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4390481409","doi":"https://doi.org/10.1109/wifs58808.2023.10374615"},"language":"en","primary_location":{"id":"doi:10.1109/wifs58808.2023.10374615","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wifs58808.2023.10374615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Workshop on Information Forensics and Security (WIFS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.10108684","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":12,"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":0.9993000030517578,"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":0.9993000030517578,"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":0.9986000061035156,"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":0.9908000230789185,"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/spectrogram","display_name":"Spectrogram","score":0.9206585884094238},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.8496297597885132},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7562918663024902},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7370121479034424},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6152725219726562},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5896750688552856},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.535300076007843},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5088048577308655},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.46254226565361023},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.43881362676620483},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.41558265686035156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.337302029132843},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10537171363830566},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09535935521125793},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09388121962547302}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9206585884094238},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.8496297597885132},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7562918663024902},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7370121479034424},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6152725219726562},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5896750688552856},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.535300076007843},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5088048577308655},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.46254226565361023},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.43881362676620483},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.41558265686035156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.337302029132843},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10537171363830566},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09535935521125793},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09388121962547302},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wifs58808.2023.10374615","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wifs58808.2023.10374615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Workshop on Information Forensics and Security (WIFS)","raw_type":"proceedings-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/462552","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/462552","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":"doi:10.5281/zenodo.10108684","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10108684","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":"doi:10.5281/zenodo.10108684","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10108684","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":false,"raw_source_name":null,"raw_type":"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"},{"id":"https://openalex.org/G346919715","display_name":null,"funder_award_id":"13N16267","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W2118774185","https://openalex.org/W2936802426","https://openalex.org/W2962858109","https://openalex.org/W2967606780","https://openalex.org/W3026777299","https://openalex.org/W3160747466","https://openalex.org/W3163596559","https://openalex.org/W3186285959","https://openalex.org/W3200527256","https://openalex.org/W4297841787","https://openalex.org/W4311591887","https://openalex.org/W4313156423","https://openalex.org/W4381198892","https://openalex.org/W6631190155","https://openalex.org/W6726497184","https://openalex.org/W6739901393","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W2070982348","https://openalex.org/W1976952689","https://openalex.org/W1984921740","https://openalex.org/W2496295964","https://openalex.org/W1842536210","https://openalex.org/W1572861854","https://openalex.org/W2069501481","https://openalex.org/W1890431648","https://openalex.org/W2253161769","https://openalex.org/W2336887028"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"address":[4],"the":[5,18,54,58,65,72,83,97,101,107,116,120],"challenge":[6],"of":[7,80,93,96,119,126],"synthetic":[8,68],"speech":[9,66],"detection,":[10],"which":[11,94],"has":[12],"become":[13],"increasingly":[14],"important":[15],"due":[16],"to":[17,36,52,82],"latest":[19],"advancements":[20],"in":[21],"text-to-speech":[22],"and":[23,39,63],"voice":[24],"conversion":[25],"technologies.":[26],"We":[27],"propose":[28],"a":[29,48,78,90],"novel":[30],"multi-task":[31],"neural":[32],"network":[33],"architecture,":[34],"designed":[35],"be":[37,76],"interpretable":[38],"specifically":[40],"tailored":[41],"for":[42],"audio":[43],"signals.":[44],"The":[45],"architecture":[46],"includes":[47],"feature":[49],"bottle-neck,":[50],"used":[51],"autoencode":[53],"input":[55,98],"spectrogram,":[56],"predict":[57],"fundamental":[59],"frequency":[60],"(f0)":[61],"trajectory,":[62],"classify":[64],"as":[67],"or":[69],"natural.":[70],"Hence,":[71],"synthesis":[73],"detection":[74],"can":[75],"considered":[77],"byproduct":[79],"attending":[81],"energy":[84],"distribution":[85],"among":[86],"vocal":[87],"formants,":[88],"providing":[89],"clear":[91],"understanding":[92],"characteristics":[95],"signal":[99],"influence":[100],"final":[102],"outcome.":[103],"Our":[104],"evaluation":[105],"on":[106],"ASVspoof":[108],"2019":[109],"LA":[110],"partition":[111],"indicates":[112],"better":[113],"performance":[114],"than":[115],"current":[117],"state":[118],"art,":[121],"with":[122],"an":[123],"AUC":[124],"score":[125],"0.900.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
