{"id":"https://openalex.org/W7224078660","doi":"https://doi.org/10.48550/arxiv.2610.37640","title":"Partially Edited Audio: Generation, Defense, and Open Problems","display_name":"Partially Edited Audio: Generation, Defense, and Open Problems","publication_year":2026,"publication_date":"2026-10-27","ids":{"openalex":"https://openalex.org/W7224078660","doi":"https://doi.org/10.48550/arxiv.2610.37640"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.37640","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.37640","pdf_url":"https://arxiv.org/pdf/2610.37640","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.37640","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160017138","display_name":"Lin Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160032915","display_name":"You Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Zhang, You","raw_affiliation_strings":["T\u00e9l\u00e9com Paris"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"T\u00e9l\u00e9com Paris","institution_ids":["https://openalex.org/I12356871"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066811192","display_name":"Nicholas Evans","orcid":"https://orcid.org/0000-0002-8459-1041","observed_orcids":["https://orcid.org/0000-0002-8459-1041"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Evans, Nicholas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160001602","display_name":"Xin Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wang, Xin","raw_affiliation_strings":["National Institute of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004717608","display_name":"David F. Harwath","orcid":"https://orcid.org/0000-0003-0206-0253","observed_orcids":["https://orcid.org/0000-0003-0206-0253"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harwath, David","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085376429","display_name":"Abhinav Dhall","orcid":"https://orcid.org/0000-0002-2230-1440","observed_orcids":["https://orcid.org/0000-0002-2230-1440"]},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dhall, Abhinav","raw_affiliation_strings":["Monash University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160049897","display_name":"Bowen Shi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Bowen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160010933","display_name":"Chengzhe Sun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sun, Chengzhe","raw_affiliation_strings":["University at Buffalo , State University of New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University at Buffalo , State University of New York","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023752172","display_name":"Siwei Lyu","orcid":"https://orcid.org/0000-0002-0992-685X","observed_orcids":["https://orcid.org/0000-0002-0992-685X"]},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lyu, Siwei","raw_affiliation_strings":["University at Buffalo , State University of New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University at Buffalo , State University of New York","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev P. Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897","observed_orcids":["https://orcid.org/0000-0001-5976-0897"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khudanpur, Sanjeev","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9779999852180481,"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":0.9779999852180481,"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":0.009800000116229057,"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":0.006399999838322401,"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/audio-editing","display_name":"audio editing","score":0.8059999942779541},{"id":"https://openalex.org/keywords/generative-audio-models","display_name":"generative audio models","score":0.8970000147819519},{"id":"https://openalex.org/keywords/audio-forgery-detection","display_name":"audio forgery detection","score":0.6050000190734863},{"id":"https://openalex.org/keywords/sound-localization","display_name":"sound localization","score":0.5529999732971191},{"id":"https://openalex.org/keywords/speaker-diarization","display_name":"speaker diarization","score":0.9039999842643738},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.8600000143051147},{"id":"https://openalex.org/keywords/audio-generation","display_name":"audio generation","score":0.32600000500679016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6585000157356262},{"id":"https://openalex.org/C2779182362","wikidata":"https://www.wikidata.org/wiki/Q17126187","display_name":"Session (web analytics)","level":2,"score":0.637499988079071},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.47519999742507935},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.38119998574256897},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.33000001311302185},{"id":"https://openalex.org/C2777601897","wikidata":"https://www.wikidata.org/wiki/Q3409113","display_name":"Presentation (obstetrics)","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.2612999975681305},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2567000091075897},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2500999867916107},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.2443999946117401}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.37640","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.37640","pdf_url":"https://arxiv.org/pdf/2610.37640","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2610.37640","doi":"https://doi.org/10.48550/arxiv.2610.37640","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.37640","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.37640","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.37640","pdf_url":"https://arxiv.org/pdf/2610.37640","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224078660.pdf","grobid_xml":"https://content.openalex.org/works/W7224078660.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7165681618","https://openalex.org/W4408355556","https://openalex.org/W7133224691","https://openalex.org/W7126008049","https://openalex.org/W7168043847","https://openalex.org/W7126230622","https://openalex.org/W7101796570","https://openalex.org/W7083685130","https://openalex.org/W4416255612","https://openalex.org/W4414459939"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2],"generative":[3],"audio":[4,30,88,112],"models":[5],"facilitate":[6],"increasingly":[7],"flexible":[8],"and":[9,15,18,47,59,81,89,118,120,128,133,140],"selective":[10],"editing":[11,113,115],"of":[12,35,106],"linguistic":[13],"content":[14],"paralinguistic,":[16],"extralinguistic,":[17],"other":[19],"attributes.":[20],"This":[21,41],"paradigm,":[22],"named":[23],"partially":[24,86],"edited":[25,87],"audio,":[26,64],"differs":[27],"from":[28,56,79],"full":[29],"generation":[31,58],"as":[32,65,94],"only":[33],"portions":[34],"the":[36,69,107],"real":[37],"recording":[38],"are":[39],"edited.":[40],"technique":[42],"can":[43],"serve":[44],"both":[45,57],"beneficial":[46],"harmful":[48,97],"applications.":[49],"We":[50,83,109],"therefore":[51],"present":[52],"a":[53,66,103],"concise":[54],"survey":[55,111],"defense":[60,122],"perspectives,":[61],"focusing":[62],"on":[63],"contribution":[67],"to":[68],"ICASSP":[70],"2027":[71],"special":[72],"session":[73],"entitled":[74],"\"Partially":[75],"Edited":[76],"Media:":[77],"Perspectives":[78],"Synthesis":[80],"Defense.\"":[82],"first":[84],"define":[85],"argue":[90],"that":[91],"what":[92],"counts":[93],"``fake''":[95],"or":[96],"is":[98],"an":[99],"application-dependent":[100],"judgment,":[101],"not":[102],"fixed":[104],"property":[105],"edit.":[108],"then":[110,121],"by":[114,124],"target,":[116],"approaches,":[117],"evaluation,":[119],"methods":[123],"detection,":[125],"localization,":[126],"diarization,":[127],"interpretability,":[129],"summarizing":[130],"representative":[131],"benchmarks":[132],"toolkits.":[134],"Finally,":[135],"we":[136],"discuss":[137],"future":[138],"directions":[139],"open":[141],"problems.":[142]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-10-29T00:00:00"}