{"id":"https://openalex.org/W4412888689","doi":"https://doi.org/10.18653/v1/2025.findings-acl.218","title":"Investigating Prosodic Signatures via Speech Pre-Trained Models for Audio Deepfake Source Attribution","display_name":"Investigating Prosodic Signatures via Speech Pre-Trained Models for Audio Deepfake Source Attribution","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888689","doi":"https://doi.org/10.18653/v1/2025.findings-acl.218"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.218","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.218","pdf_url":"https://aclanthology.org/2025.findings-acl.218.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.218.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099056917","display_name":"Orchid Chetia Phukan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Orchid Chetia Phukan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111233214","display_name":"Drishti Singh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Drishti Singh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014658425","display_name":"Swarup Ranjan Behera","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Swarup Ranjan Behera","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014100784","display_name":"Arun Balaji Buduru","orcid":"https://orcid.org/0000-0002-6267-8138"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arun Balaji Buduru","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5011512226","display_name":"Rajesh Sharma","orcid":"https://orcid.org/0000-0003-3581-1332"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajesh Sharma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":"4206","last_page":"4214"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9911999702453613,"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":0.9911999702453613,"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/T11309","display_name":"Music and Audio Processing","score":0.9753000140190125,"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":0.9735000133514404,"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":0.7736005783081055},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6441664695739746},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4748150110244751},{"id":"https://openalex.org/keywords/attribution","display_name":"Attribution","score":0.4738854765892029},{"id":"https://openalex.org/keywords/source-model","display_name":"Source model","score":0.45479658246040344},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.41044285893440247},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3664807975292206},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1019316017627716},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.06875145435333252}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7736005783081055},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6441664695739746},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4748150110244751},{"id":"https://openalex.org/C143299363","wikidata":"https://www.wikidata.org/wiki/Q900584","display_name":"Attribution","level":2,"score":0.4738854765892029},{"id":"https://openalex.org/C2985998994","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Source model","level":2,"score":0.45479658246040344},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.41044285893440247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3664807975292206},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1019316017627716},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.06875145435333252},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.218","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.218","pdf_url":"https://aclanthology.org/2025.findings-acl.218.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.218","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.218","pdf_url":"https://aclanthology.org/2025.findings-acl.218.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888689.pdf","grobid_xml":"https://content.openalex.org/works/W4412888689.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2035546108","https://openalex.org/W2376361520","https://openalex.org/W2133328864","https://openalex.org/W2093949997","https://openalex.org/W2570200690","https://openalex.org/W1911859126","https://openalex.org/W2120730869","https://openalex.org/W1569721167","https://openalex.org/W2541680182","https://openalex.org/W2166699153"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,145,166],"investigate":[4],"various":[5,59],"state-of-theart":[6],"(SOTA)":[7],"speech":[8,134],"pre-trained":[9],"models":[10],"(PTMs)":[11],"for":[12,23,38,71,113,152],"their":[13],"capability":[14],"to":[15,43,90,105,142,173],"capture":[16],"prosodic":[17,29,52,69,116],"signatures":[18,37],"of":[19,35,118,138,155,159],"the":[20,48,55,85,92,119,147,168,175],"generative":[21],"sources":[22,120],"audio":[24,130],"deepfake":[25,131],"source":[26],"attribution":[27],"(ADSD).These":[28],"characteristics":[30,117],"can":[31,102],"be":[32,103],"considered":[33,94],"one":[34],"major":[36],"ADSD,":[39],"which":[40],"is":[41,47],"unique":[42,115],"each":[44],"source.So":[45],"better":[46,54,123],"PTM":[49],"at":[50],"capturing":[51,114],"signs":[53],"ADSD":[56],"performance.We":[57],"consider":[58],"SOTA":[60,186],"PTMs":[61,93,139,177],"that":[62,110],"have":[63],"shown":[64],"top":[65],"performance":[66,87,101,170],"in":[67,88,121,171],"different":[68],"tasks":[70,127],"our":[72],"experiments":[73],"on":[74],"benchmark":[75],"datasets,":[76],"ASVSpoof":[77],"2019":[78],"and":[79,133,149,161,184],"CFAD.x-vector":[80],"(speaker":[81],"recognition":[82,108],"PTM)":[83],"attains":[84],"highest":[86],"comparison":[89,172],"all":[91,174],"despite":[95],"consisting":[96],"lowest":[97],"model":[98],"parameters.This":[99],"higher":[100],"due":[104],"its":[106],"speaker":[107],"pre-training":[109],"enables":[111],"it":[112],"a":[122],"way.Further,":[124],"motivated":[125],"from":[126],"such":[128,156],"as":[129,178,180],"detection":[132],"recognition,":[135],"where":[136],"fusion":[137,154,158,182],"representations":[140,163],"lead":[141],"improved":[143],"performance,":[144],"explore":[146],"same":[148],"propose":[150],"FINDER":[151],"effective":[153],"representations.With":[157],"Whisper":[160],"x-vector":[162],"through":[164],"FINDER,":[165],"achieved":[167],"topmost":[169],"individual":[176],"well":[179],"baseline":[181],"techniques":[183],"attaining":[185],"performance.":[187]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}