{"id":"https://openalex.org/W4412945512","doi":"https://doi.org/10.18653/v1/2025.acl-long.493","title":"SpeechFake: A Large-Scale Multilingual Speech Deepfake Dataset Incorporating Cutting-Edge Generation Methods","display_name":"SpeechFake: A Large-Scale Multilingual Speech Deepfake Dataset Incorporating Cutting-Edge Generation Methods","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945512","doi":"https://doi.org/10.18653/v1/2025.acl-long.493"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.493","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.493","pdf_url":"https://aclanthology.org/2025.acl-long.493.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.493.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004675212","display_name":"Wen Huang","orcid":"https://orcid.org/0000-0001-7682-4354"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005181515","display_name":"Ying-Qiu Gu","orcid":"https://orcid.org/0000-0001-9225-9084"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanmei Gu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049694267","display_name":"Zhiming Wang","orcid":"https://orcid.org/0000-0002-4854-2170"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiming Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110390049","display_name":"Huijia Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huijia Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanmin Qian","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":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9985","last_page":"9998"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9909999966621399,"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":0.9909999966621399,"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":0.968999981880188,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.967199981212616,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7329578399658203},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6377068161964417},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.631091296672821},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47030967473983765},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4113209843635559},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3252256214618683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7329578399658203},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6377068161964417},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.631091296672821},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47030967473983765},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4113209843635559},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3252256214618683},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.493","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.493","pdf_url":"https://aclanthology.org/2025.acl-long.493.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.493","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.493","pdf_url":"https://aclanthology.org/2025.acl-long.493.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1899722019","display_name":"\u6df1\u5ea6\u5b66\u4e60\u8bed\u97f3\u8bc6\u522b\u4e2d\u7684\u5feb\u901f\u9ad8\u6548\u81ea\u9002\u5e94\u65b9\u6cd5\u7814\u7a76","funder_award_id":"62071288","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3537961753","display_name":null,"funder_award_id":"62122050","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5465080215","display_name":null,"funder_award_id":"2021SHZDZX0102","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G8721642152","display_name":null,"funder_award_id":"2021SHZDZX0102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320318398","display_name":"Ant Group","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945512.pdf","grobid_xml":"https://content.openalex.org/works/W4412945512.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3188962172","https://openalex.org/W2052899165","https://openalex.org/W2008562718","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2131146434","https://openalex.org/W2951359407","https://openalex.org/W3204019825"],"abstract_inverted_index":{"As":[0],"speech":[1,28,62,82,176],"generation":[2,91,157,186],"technology":[3],"advances,":[4],"the":[5,19,101,120],"risk":[6],"of":[7,76,90,119],"misuse":[8],"through":[9],"deepfake":[10,29,63,69,177],"audio":[11],"has":[12],"become":[13],"a":[14,56,87,116,171],"pressing":[15],"concern,":[16],"which":[17],"underscores":[18],"critical":[20],"need":[21],"for":[22,61,174,184],"robust":[23,182],"detection":[24,132,165,178],"systems.However,":[25],"many":[26],"existing":[27],"datasets":[30],"are":[31],"limited":[32],"in":[33],"scale":[34],"and":[35,97,124,145,161,179],"diversity,":[36,160],"making":[37],"it":[38],"challenging":[39],"to":[40,47,153],"train":[41],"models":[42,133,183],"that":[43],"can":[44],"generalize":[45],"well":[46],"unseen":[48,147],"deepfakes.To":[49],"address":[50],"these":[51],"gaps,":[52],"we":[53,114,150],"introduce":[54],"SpeechFake,":[55,135],"largescale":[57],"dataset":[58,85],"designed":[59],"specifically":[60],"detection.SpeechFake":[64],"includes":[65],"over":[66],"3":[67],"million":[68],"samples,":[70],"totaling":[71],"more":[72,181],"than":[73],"3,000":[74],"hours":[75],"audio,":[77],"generated":[78],"using":[79],"40":[80],"different":[81],"synthesis":[83],"tools.The":[84],"encompasses":[86],"wide":[88],"range":[89],"techniques,":[92],"including":[93],"text-to-speech,":[94],"voice":[95],"conversion,":[96],"neural":[98],"vocoder,":[99],"incorporating":[100],"latest":[102],"cuttingedge":[103],"methods.It":[104],"also":[105,126],"provides":[106],"multilingual":[107],"support,":[108],"spanning":[109],"46":[110],"languages.In":[111],"this":[112],"paper,":[113],"offer":[115],"detailed":[117],"overview":[118],"dataset's":[121],"creation,":[122],"composition,":[123],"statistics.We":[125],"present":[127],"baseline":[128],"results":[129],"by":[130],"training":[131],"on":[134,139],"demonstrating":[136],"strong":[137],"performance":[138],"both":[140],"its":[141],"own":[142],"test":[143,148],"sets":[144],"various":[146],"sets.Additionally,":[149],"conduct":[151],"experiments":[152],"rigorously":[154],"explore":[155],"how":[156],"methods,":[158],"language":[159],"speaker":[162],"variation":[163],"affect":[164],"performance.We":[166],"believe":[167],"SpeechFake":[168],"will":[169],"be":[170],"valuable":[172],"resource":[173],"advancing":[175],"developing":[180],"evolving":[185],"techniques":[187],"1":[188],".":[189]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}