{"id":"https://openalex.org/W7166855072","doi":"https://doi.org/10.18653/v1/2026.findings-acl.285","title":"RTCFake: Speech Deepfake Detection in Real-Time Communication","display_name":"RTCFake: Speech Deepfake Detection in Real-Time Communication","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166855072","doi":"https://doi.org/10.18653/v1/2026.findings-acl.285"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.285","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.285","pdf_url":"https://aclanthology.org/2026.findings-acl.285.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 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.285.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139781608","display_name":"Jun Xue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Xue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124403526","display_name":"Zhuolin Yi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuolin Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139779513","display_name":"Yihuan Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yihuan Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139772952","display_name":"Yanzhen Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanzhen Ren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139746723","display_name":"Yujie Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujie Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037493212","display_name":"Cunhang Fan","orcid":"https://orcid.org/0000-0001-6318-8803"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cunhang Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134777906","display_name":"Zicheng Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zicheng Su","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139806425","display_name":"Yongcheng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongcheng Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139829631","display_name":"Bo Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Cai","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.84445154,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5763","last_page":"5775"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.4262999892234802,"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":0.4262999892234802,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.258899986743927,"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/T10860","display_name":"Speech and Audio Processing","score":0.0471000000834465,"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/noise","display_name":"Noise (video)","score":0.2858000099658966},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.2662999927997589},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2418999969959259},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2410999983549118},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.23690000176429749}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5835000276565552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3991999924182892},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.31470000743865967},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2858000099658966},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2418999969959259},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2410999983549118},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.24009999632835388},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.23690000176429749},{"id":"https://openalex.org/C137270730","wikidata":"https://www.wikidata.org/wiki/Q120811","display_name":"Detection theory","level":3,"score":0.22619999945163727}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.285","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.285","pdf_url":"https://aclanthology.org/2026.findings-acl.285.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 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.285","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.285","pdf_url":"https://aclanthology.org/2026.findings-acl.285.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 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166855072.pdf","grobid_xml":"https://content.openalex.org/works/W7166855072.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,8,34,57,117,154,180],"rapid":[2],"advancement":[3],"of":[4],"speech":[5,12,43,60,78,151],"generation":[6],"technologies,":[7],"threat":[9],"posed":[10],"by":[11,76],"deepfakes":[13],"in":[14,161,179],"real-time":[15],"communication":[16],"(RTC)":[17],"scenarios":[18],"has":[19],"intensified.However,":[20],"existing":[21],"detection":[22],"studies":[23],"mainly":[24],"focus":[25],"on":[26],"offline":[27,93],"simulations":[28],"and":[29,49,84,94,125,136,146,165,171],"struggle":[30],"to":[31,109],"cope":[32],"with":[33],"complex":[35,138],"distortions":[36],"introduced":[37],"during":[38],"RTC":[39,65,134],"transmission,":[40],"including":[41],"unknown":[42],"enhancement":[44],"processes":[45],"(e.g.,":[46,87],"noise":[47,139,166],"suppression)":[48],"codec":[50],"compression.To":[51],"address":[52],"this":[53,115],"challenge,":[54],"we":[55,98],"present":[56],"first":[58],"large-scale":[59],"deepfake":[61,152],"dataset":[62,73,119,176],"tailored":[63],"for":[64,150],"scenarios,":[66],"termed":[67],"RTCFake,":[68],"totaling":[69],"approximately":[70],"600":[71],"hours.The":[72],"is":[74,120,177],"constructed":[75],"transmitting":[77],"through":[79],"multiple":[80],"mainstream":[81],"social":[82],"media":[83],"conferencing":[85],"platforms":[86,135],"Zoom),":[88],"enabling":[89],"precise":[90],"pairing":[91],"between":[92],"online":[95],"speech.In":[96],"addition,":[97],"propose":[99],"a":[100,143],"phoneme-guided":[101],"consistency":[102],"learning":[103],"(PCL)":[104],"strategy":[105,157],"that":[106],"enforces":[107],"models":[108],"learn":[110],"platform-invariant":[111],"semantic":[112],"structural":[113],"representations.In":[114],"paper,":[116],"RTCFake":[118,175],"divided":[121],"into":[122],"training,":[123],"development,":[124],"evaluation":[126,128,148],"sets.The":[127],"set":[129],"further":[130],"includes":[131],"both":[132,162],"unseen":[133,137],"conditions,":[140],"thereby":[141],"providing":[142],"more":[144],"realistic":[145],"challenging":[147],"benchmark":[149],"detection.Furthermore,":[153],"proposed":[155],"PCL":[156],"achieves":[158],"significant":[159],"improvements":[160],"cross-platform":[163],"generalization":[164],"robustness,":[167],"offering":[168],"an":[169],"effective":[170],"generalizable":[172],"modeling":[173],"paradigm.The":[174],"provided":[178],"https://huggingface.co/":[181],"datasets/JunXueTech/RTCFake.":[182]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}