{"id":"https://openalex.org/W4408355324","doi":"https://doi.org/10.1109/icassp49660.2025.10889913","title":"PET: High-Frequency Temporal Self-Consistency Learning for Partially Deepfake Audio Localization","display_name":"PET: High-Frequency Temporal Self-Consistency Learning for Partially Deepfake Audio Localization","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355324","doi":"https://doi.org/10.1109/icassp49660.2025.10889913"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889913","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889913","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5001846517","display_name":"Jiayi He","orcid":"https://orcid.org/0009-0001-1461-5714"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayi He","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078525423","display_name":"Jiangyan Yi","orcid":"https://orcid.org/0000-0003-2422-4618"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangyan Yi","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113375262","display_name":"Jianhua Tao","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111226573","display_name":"Siding Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siding Zeng","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9908000230789185,"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":0.9908000230789185,"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":0.9884999990463257,"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":0.9704999923706055,"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":0.7292152047157288},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.7200354337692261},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46977752447128296},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3774389326572418}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7292152047157288},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7200354337692261},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46977752447128296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3774389326572418}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889913","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889913","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2034139177","https://openalex.org/W2120390927","https://openalex.org/W2176804518","https://openalex.org/W3003257820","https://openalex.org/W3048786211","https://openalex.org/W3104914837","https://openalex.org/W3196774886","https://openalex.org/W3197457172","https://openalex.org/W3198533616","https://openalex.org/W4221138880","https://openalex.org/W4224920249","https://openalex.org/W4225275505","https://openalex.org/W4311599471","https://openalex.org/W4313306150","https://openalex.org/W4319586289","https://openalex.org/W4319780207","https://openalex.org/W4375869244","https://openalex.org/W4385999783","https://openalex.org/W4391827480","https://openalex.org/W4392903271","https://openalex.org/W4402112367","https://openalex.org/W6852755086","https://openalex.org/W6929597477"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Partially":[0],"deepfake":[1,19,54],"audio":[2,20,55],"attacks":[3],"have":[4],"attracted":[5],"the":[6,10,14,39,82,99,104,109],"attention":[7],"recently,":[8],"and":[9,111],"demand":[11],"for":[12,52],"locating":[13],"manipulation":[15],"regions":[16],"of":[17,42,98,115],"partially":[18,53],"arises":[21],"accordingly.":[22],"However,":[23],"existing":[24],"methods":[25],"are":[26],"usually":[27],"proposed":[28],"based":[29,57],"on":[30,58,103],"frame-level":[31],"authenticity":[32],"detection":[33],"or":[34],"splicing":[35],"boundaries":[36],"detection,":[37],"neglecting":[38],"temporal":[40,59],"self-consistency":[41,60],"audio.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47],"propose":[48],"a":[49],"novel":[50],"method":[51],"localization":[56],"learning":[61],"via":[62],"high-frequency":[63],"components,":[64],"named":[65],"as":[66],"PET.":[67,116],"The":[68],"results":[69],"demonstrates":[70],"that,":[71],"in":[72],"ADD":[73],"2023":[74],"Track":[75],"2":[76],"eval":[77],"set,":[78],"it":[79],"could":[80],"achieve":[81],"segment":[83],"F1-score":[84],"at":[85],"0.7397":[86],"without":[87],"any":[88],"data":[89],"augmentation":[90],"strategies,":[91],"which":[92],"is":[93],"21.94%":[94],"higher":[95],"than":[96],"that":[97],"system":[100],"ranked":[101],"1st":[102],"leaderboard.":[105],"It":[106],"also":[107],"confirms":[108],"effectiveness":[110],"well":[112],"generalization":[113],"ability":[114]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}