{"id":"https://openalex.org/W7166830663","doi":"https://doi.org/10.18653/v1/2026.acl-long.796","title":"A Data-Centric Approach to Generalizable Speech Deepfake Detection","display_name":"A Data-Centric Approach to Generalizable Speech Deepfake Detection","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166830663","doi":"https://doi.org/10.18653/v1/2026.acl-long.796"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.796","doi":"https://doi.org/10.18653/v1/2026.acl-long.796","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.796","pdf_url":"https://aclanthology.org/2026.acl-long.796.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.acl-long.796.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121176511","display_name":"Wen Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Huang","raw_affiliation_strings":["Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence , AI Institute School of Computer Science , Shanghai Jiao Tong University , China \u266d"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence , AI Institute School of Computer Science , Shanghai Jiao Tong University , China \u266d","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139740733","display_name":"Yuchen Mao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210161490","display_name":"Viet Tri University of Industry","ror":"https://ror.org/059sj0146","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210161490"]}],"countries":["CN","VN"],"is_corresponding":false,"raw_author_name":"Yuchen Mao","raw_affiliation_strings":["Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence , AI Institute School of Computer Science , Shanghai Jiao Tong University , China \u266d","VUI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence , AI Institute School of Computer Science , Shanghai Jiao Tong University , China \u266d","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"VUI Labs","institution_ids":["https://openalex.org/I4210161490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139827005","display_name":"Yanmin Qian","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence , AI Institute School of Computer Science , Shanghai Jiao Tong University , China \u266d"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence , AI Institute School of Computer Science , Shanghai Jiao Tong University , China \u266d","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.44843918,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17520","last_page":"17539"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9872999787330627,"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":0.9872999787330627,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.00800000037997961,"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":0.0017999999690800905,"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/speech-deepfake-detection","display_name":"speech deepfake detection","score":1.0},{"id":"https://openalex.org/keywords/data-centric-ai","display_name":"data-centric AI","score":0.5329999923706055},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.6470000147819519},{"id":"https://openalex.org/keywords/data-aggregation","display_name":"data aggregation","score":0.6859999895095825},{"id":"https://openalex.org/keywords/data-pruning","display_name":"data pruning","score":0.8889999985694885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5906999707221985},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4641999900341034},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.33730000257492065},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2797999978065491},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2500999867916107},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.24729999899864197}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.796","doi":"https://doi.org/10.18653/v1/2026.acl-long.796","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.796","pdf_url":"https://aclanthology.org/2026.acl-long.796.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.796","doi":"https://doi.org/10.18653/v1/2026.acl-long.796","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.796","pdf_url":"https://aclanthology.org/2026.acl-long.796.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5987393275","display_name":null,"funder_award_id":"U25A20409","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322999","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166830663.pdf","grobid_xml":"https://content.openalex.org/works/W7166830663.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4408354101","https://openalex.org/W4412945512","https://openalex.org/W4415433580","https://openalex.org/W4415433424","https://openalex.org/W7172015077","https://openalex.org/W7151524114","https://openalex.org/W4387665604","https://openalex.org/W7138846099","https://openalex.org/W7212264226","https://openalex.org/W7202364773"],"abstract_inverted_index":{"Achieving":[0],"robust":[1],"generalization":[2],"in":[3],"speech":[4],"deepfake":[5],"detection":[6],"(SDD)":[7],"remains":[8],"a":[9,39,52,65,95,133,160],"primary":[10],"challenge,":[11],"as":[12],"models":[13],"often":[14,35],"fail":[15],"to":[16,69],"detect":[17],"unseen":[18],"forgery":[19],"methods.While":[20],"research":[21],"has":[22],"focused":[23],"on":[24,132,155],"model-centric":[25],"and":[26,55,82,107,152,159],"algorithm-centric":[27],"solutions,":[28],"the":[29,43,60,71,78,86,90,115,124,139],"impact":[30,79],"of":[31,80,123,164],"data":[32,45,72,101,136,151],"composition":[33],"is":[34],"underexplored.This":[36],"paper":[37],"proposes":[38],"datacentric":[40],"approach,":[41],"analyzing":[42],"SDD":[44],"landscape":[46],"from":[47],"two":[48,103],"practical":[49],"perspectives:":[50],"constructing":[51],"single":[53],"dataset":[54],"aggregating":[56],"multiple":[57],"datasets.To":[58],"address":[59,85],"first":[61],"perspective,":[62],"we":[63,88],"conduct":[64],"large-scale":[66,147],"empirical":[67],"study":[68],"characterize":[70],"scaling":[73],"laws":[74],"for":[75,98],"SDD,":[76],"quantifying":[77],"source":[81],"generator":[83],"diversity.To":[84],"second,":[87],"propose":[89],"Diversity-Optimized":[91],"Sampling":[92],"Strategy":[93],"(DOSS),":[94],"principled":[96],"framework":[97],"mixing":[99],"heterogeneous":[100],"with":[102,149],"implementations:":[104],"DOSS-Select":[105,113],"(pruning)":[106],"DOSS-Weight":[108,141],"(re-weighting).Our":[109],"experiments":[110],"show":[111],"that":[112],"outperforms":[114],"naive":[116],"aggregation":[117],"baseline":[118],"while":[119],"using":[120,138],"only":[121],"3%":[122],"total":[125],"available":[126],"data.Furthermore,":[127],"our":[128],"final":[129],"model,":[130],"trained":[131],"12k-hour":[134],"curated":[135],"pool":[137],"optimal":[140],"strategy,":[142],"achieves":[143],"state-of-the-art":[144],"performance,":[145],"outperforming":[146],"baselines":[148],"greater":[150],"model":[153],"efficiency":[154],"both":[156],"public":[157],"benchmarks":[158],"new":[161],"challenge":[162],"set":[163],"various":[165],"commercial":[166],"APIs.":[167]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2026-07-02T00:00:00"}