{"id":"https://openalex.org/W7161583468","doi":"https://doi.org/10.1109/access.2026.3694045","title":"MIST: A Multilingual Dataset and Benchmark for Fine-Grained Audio Inpainting Tampering Localization","display_name":"MIST: A Multilingual Dataset and Benchmark for Fine-Grained Audio Inpainting Tampering Localization","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7161583468","doi":"https://doi.org/10.1109/access.2026.3694045"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3694045","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3694045","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3694045","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135324858","display_name":"Tung Vu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095603","display_name":"Vietnam Posts and Telecommunications Group (Vietnam)","ror":"https://ror.org/00q0e7f94","country_code":"VN","type":"company","lineage":["https://openalex.org/I4210095603"]},{"id":"https://openalex.org/I4400600977","display_name":"Posts and Telecommunications Institute of Technology","ror":"https://ror.org/0363rtq22","country_code":null,"type":"education","lineage":["https://openalex.org/I4400600977"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Tung Vu","raw_affiliation_strings":["Posts and Telecommunications Institute of Technology, Hanoi, Vietnam"],"raw_orcid":"https://orcid.org/0009-0001-7188-5972","affiliations":[{"raw_affiliation_string":"Posts and Telecommunications Institute of Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I4210095603","https://openalex.org/I4400600977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135405680","display_name":"Yen Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095603","display_name":"Vietnam Posts and Telecommunications Group (Vietnam)","ror":"https://ror.org/00q0e7f94","country_code":"VN","type":"company","lineage":["https://openalex.org/I4210095603"]},{"id":"https://openalex.org/I4400600977","display_name":"Posts and Telecommunications Institute of Technology","ror":"https://ror.org/0363rtq22","country_code":null,"type":"education","lineage":["https://openalex.org/I4400600977"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Yen Nguyen","raw_affiliation_strings":["Posts and Telecommunications Institute of Technology, Hanoi, Vietnam"],"raw_orcid":"https://orcid.org/0009-0006-9026-4692","affiliations":[{"raw_affiliation_string":"Posts and Telecommunications Institute of Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I4210095603","https://openalex.org/I4400600977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088039595","display_name":"Hai V. Nguyen","orcid":"https://orcid.org/0000-0002-2578-170X"},"institutions":[{"id":"https://openalex.org/I4210095603","display_name":"Vietnam Posts and Telecommunications Group (Vietnam)","ror":"https://ror.org/00q0e7f94","country_code":"VN","type":"company","lineage":["https://openalex.org/I4210095603"]},{"id":"https://openalex.org/I4400600977","display_name":"Posts and Telecommunications Institute of Technology","ror":"https://ror.org/0363rtq22","country_code":null,"type":"education","lineage":["https://openalex.org/I4400600977"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Hai Nguyen","raw_affiliation_strings":["Posts and Telecommunications Institute of Technology, Hanoi, Vietnam"],"raw_orcid":"https://orcid.org/0009-0009-4445-2811","affiliations":[{"raw_affiliation_string":"Posts and Telecommunications Institute of Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I4210095603","https://openalex.org/I4400600977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136381118","display_name":"Cuong Pham","orcid":"https://orcid.org/0000-0003-0973-0889"},"institutions":[{"id":"https://openalex.org/I4210095603","display_name":"Vietnam Posts and Telecommunications Group (Vietnam)","ror":"https://ror.org/00q0e7f94","country_code":"VN","type":"company","lineage":["https://openalex.org/I4210095603"]},{"id":"https://openalex.org/I4400600977","display_name":"Posts and Telecommunications Institute of Technology","ror":"https://ror.org/0363rtq22","country_code":null,"type":"education","lineage":["https://openalex.org/I4400600977"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Cuong Pham","raw_affiliation_strings":["Posts and Telecommunications Institute of Technology, Hanoi, Vietnam"],"raw_orcid":"https://orcid.org/0000-0003-0973-0889","affiliations":[{"raw_affiliation_string":"Posts and Telecommunications Institute of Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I4210095603","https://openalex.org/I4400600977"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124960734","display_name":"Cong Tran","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095603","display_name":"Vietnam Posts and Telecommunications Group (Vietnam)","ror":"https://ror.org/00q0e7f94","country_code":"VN","type":"company","lineage":["https://openalex.org/I4210095603"]},{"id":"https://openalex.org/I4400600977","display_name":"Posts and Telecommunications Institute of Technology","ror":"https://ror.org/0363rtq22","country_code":null,"type":"education","lineage":["https://openalex.org/I4400600977"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Cong Tran","raw_affiliation_strings":["Posts and Telecommunications Institute of Technology, Hanoi, Vietnam"],"raw_orcid":"https://orcid.org/0000-0001-9467-4978","affiliations":[{"raw_affiliation_string":"Posts and Telecommunications Institute of Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I4210095603","https://openalex.org/I4400600977"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.58995327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"76700","last_page":"76721"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.38609999418258667,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.38609999418258667,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.34389999508857727,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12357","display_name":"Digital Media Forensic Detection","score":0.12710000574588776,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/benchmark","display_name":"Benchmark (surveying)","score":0.6970999836921692},{"id":"https://openalex.org/keywords/inpainting","display_name":"Inpainting","score":0.6575999855995178},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3165000081062317},{"id":"https://openalex.org/keywords/electronic-mail","display_name":"Electronic mail","score":0.29319998621940613},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2847999930381775}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8202000260353088},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6970999836921692},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.6575999855995178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6305000185966492},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3977999985218048},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33090001344680786},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C3020028006","wikidata":"https://www.wikidata.org/wiki/Q9158","display_name":"Electronic mail","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27379998564720154},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2703000009059906}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2026.3694045","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3694045","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2605.02223","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.02223","pdf_url":"https://arxiv.org/pdf/2605.02223","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:doaj.org/article:e3c11b78965c4c289df0bc524ca12366","is_oa":true,"landing_page_url":"https://doaj.org/article/e3c11b78965c4c289df0bc524ca12366","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 76700-76721 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3694045","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3694045","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Partial":[0],"speech":[1,147],"inpainting,":[2],"replacing":[3],"a":[4,8,58,93,102,120],"few":[5],"words":[6],"within":[7],"genuine":[9],"utterance":[10],"via":[11],"voice":[12,80],"cloning":[13],"to":[14,42,171],"alter":[15],"its":[16],"meaning,":[17],"is":[18,187],"an":[19],"emerging":[20],"audio":[21],"deepfake":[22],"threat.":[23],"Unlike":[24],"fully":[25,145],"synthesized":[26,146],"speech,":[27],"the":[28,35,165,174,184],"manipulated":[29],"content":[30],"constitutes":[31],"only":[32],"2\u20137%":[33],"of":[34,52,115],"utterance,":[36,72],"and":[37,78,118,134,173,197],"existing":[38],"benchmarks":[39],"are":[40,200],"limited":[41],"single-region":[43],"tampering":[44],"with":[45,65,87],"utterance-level":[46,141],"labels.":[47],"To":[48,91],"enable":[49],"systematic":[50],"study":[51],"this":[53,96],"problem,":[54],"we":[55,98],"introduce":[56,100],"MIST,":[57],"large-scale":[59],"multilingual":[60],"dataset":[61],"spanning":[62],"six":[63],"languages":[64],"1\u20133":[66],"independently":[67],"inpainted":[68],"word-level":[69],"segments":[70],"per":[71],"generated":[73],"through":[74],"LLM-guided":[75],"semantic":[76],"replacement":[77],"neural":[79],"cloning,":[81],"totaling":[82],"approximately":[83],"497k":[84],"tampered":[85,110],"utterances":[86],"precise":[88],"temporal":[89,126],"annotations.":[90],"establish":[92],"benchmark":[94],"for":[95],"task,":[97],"further":[99],"ISA,":[101],"backbone-agnostic":[103],"coarse-to-fine":[104],"localization":[105],"framework":[106],"that":[107,129,140,183],"recovers":[108],"all":[109,155],"regions":[111],"without":[112],"prior":[113],"knowledge":[114],"their":[116],"count;":[117],"SF1@\u03c4,":[119],"segment-level":[121],"F1":[122],"metric":[123],"based":[124],"on":[125,144,149,159],"IoU":[127],"matching":[128],"jointly":[130],"evaluates":[131],"region":[132],"counting":[133],"boundary":[135],"precision.":[136],"Zero-shot":[137],"experiments":[138],"confirm":[139],"classifiers":[142],"trained":[143],"fail":[148],"MIST":[150,160],"(SF1@0.5":[151],"\u2264":[152],"1.7%":[153],"across":[154],"backbones),":[156],"while":[157],"fine-tuning":[158],"annotations":[161],"dramatically":[162],"improves":[163,168],"performance:":[164],"Wav2Vec2-AASIST":[166],"backbone":[167,176],"from":[169],"1.2%":[170],"29.2%,":[172],"strongest":[175],"(WavLM-AASIST)":[177],"reaches":[178],"SF1@0.5":[179],"=":[180],"33.5%,":[181],"demonstrating":[182],"primary":[185],"bottleneck":[186],"training":[188],"data":[189],"rather":[190],"than":[191],"inference":[192],"methodology.":[193],"The":[194],"dataset,":[195],"code,":[196],"evaluation":[198],"toolkit":[199],"publicly":[201],"available.":[202]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-05-19T00:00:00"}