{"id":"https://openalex.org/W4394022294","doi":"https://doi.org/10.5281/zenodo.6560159","title":"TIMIT-TTS: a Text-to-Speech Dataset for Synthetic Speech Detection","display_name":"TIMIT-TTS: a Text-to-Speech Dataset for Synthetic Speech Detection","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4394022294","doi":"https://doi.org/10.5281/zenodo.6560159"},"language":"en","primary_location":{"id":"pmh:oai:zenodo.org:6560159","is_oa":true,"landing_page_url":"https://zenodo.org/record/6560159","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/6560159","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033038241","display_name":"Davide Salvi","orcid":"https://orcid.org/0000-0002-5163-3364"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Salvi, Davide","raw_affiliation_strings":["Politecnico di Milano, Italy"],"raw_orcid":"https://orcid.org/0000-0002-5163-3364","affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047571817","display_name":"Brian Hosler","orcid":"https://orcid.org/0000-0002-4590-587X"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hosler, Brian","raw_affiliation_strings":["Drexel University, USA"],"raw_orcid":"https://orcid.org/0000-0002-4590-587X","affiliations":[{"raw_affiliation_string":"Drexel University, USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051370303","display_name":"Paolo Bestagini","orcid":"https://orcid.org/0000-0003-0406-0222"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Bestagini, Paolo","raw_affiliation_strings":["Politecnico di Milano, Italy"],"raw_orcid":"https://orcid.org/0000-0003-0406-0222","affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023433042","display_name":"Matthew C. Stamm","orcid":"https://orcid.org/0000-0002-3986-4039"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stamm, Matthew C.","raw_affiliation_strings":["Drexel University, USA"],"raw_orcid":"https://orcid.org/0000-0002-3986-4039","affiliations":[{"raw_affiliation_string":"Drexel University, USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005378965","display_name":"Stefano Tubaro","orcid":"https://orcid.org/0000-0002-1990-9869"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Tubaro, Stefano","raw_affiliation_strings":["Politecnico di Milano, Italy"],"raw_orcid":"https://orcid.org/0000-0002-1990-9869","affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"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":0.9848999977111816,"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":0.9848999977111816,"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":0.9350000023841858,"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-recognition","display_name":"Speech recognition","score":0.7508158683776855},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.75030517578125},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.623845636844635},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.478725403547287},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43668609857559204},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.42758694291114807},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38210025429725647},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3319036364555359},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.22472050786018372}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7508158683776855},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.75030517578125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.623845636844635},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.478725403547287},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43668609857559204},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.42758694291114807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38210025429725647},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3319036364555359},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.22472050786018372}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:zenodo.org:6560159","is_oa":true,"landing_page_url":"https://zenodo.org/record/6560159","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"},{"id":"doi:10.5281/zenodo.6560159","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.6560159","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:6560159","is_oa":true,"landing_page_url":"https://zenodo.org/record/6560159","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2071828724","https://openalex.org/W1994694193","https://openalex.org/W2161865195","https://openalex.org/W3135230428","https://openalex.org/W170831052","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W2550171623","https://openalex.org/W114661351","https://openalex.org/W596245619"],"abstract_inverted_index":{"With":[0],"the":[1,8,22,29,61,72,83,96,102,127,152,169,177,189,198,224,250,262,267,298,315,327],"rapid":[2],"development":[3],"of":[4,12,98,105,171,179,200,226,330],"deep":[5],"learning":[6],"techniques,":[7],"generation":[9,199],"and":[10,51,63,162,187,236,254,283,306,310,321],"counterfeiting":[11],"multimedia":[13,78,99],"material":[14],"are":[15,48,70,137],"becoming":[16,138],"increasingly":[17],"straightforward":[18],"to":[19,168,176,185,242,252,287,296],"perform.":[20],"At":[21],"same":[23],"time,":[24],"sharing":[25],"fake":[26,221],"content":[27,215],"on":[28,197],"web":[30],"has":[31,81],"become":[32],"so":[33],"simple":[34],"that":[35,69,86,94,158],"malicious":[36],"users":[37],"can":[38,66,271],"create":[39],"unpleasant":[40],"situations":[41],"with":[42,54,281],"minimal":[43],"effort.":[44],"Also,":[45],"forged":[46,182],"media":[47],"getting":[49],"more":[50,52,322],"complex,":[53],"manipulated":[55,135],"videos":[56,136],"(e.g.,":[57],"deepfakes":[58],"where":[59],"both":[60,160,302],"visual":[62],"audio":[64,161,277,309],"contents":[65],"be":[67,144,272],"counterfeited)":[68],"taking":[71],"scene":[73],"over":[74],"still":[75,123],"images.<br>":[76],"The":[77,230],"forensic":[79,319],"community":[80],"addressed":[82],"possible":[84],"threats":[85],"this":[87,193],"situation":[88],"could":[89,143],"imply":[90],"by":[91],"developing":[92,172],"detectors":[93,156,320],"verify":[95],"authenticity":[97],"objects.":[100],"However,":[101],"vast":[103],"majority":[104],"these":[106],"tools":[107],"only":[108],"analyze":[109],"one":[110],"modality":[111],"at":[112],"a":[113,118,149,208,217,257,275],"time.<br>":[114],"This":[115,165,270,313],"was":[116],"not":[117],"problem":[119],"as":[120,122,274],"long":[121],"images":[124],"were":[125],"considered":[126],"most":[128,263],"widely":[129],"edited":[130],"media,":[131],"but":[132,174],"now,":[133],"since":[134],"customary,":[139],"performing":[140],"monomodal":[141,303],"analyses":[142],"reductive.":[145],"Nonetheless,":[146],"there":[147],"is":[148,166],"lack":[150],"in":[151,266,301],"literature":[153],"regarding":[154],"multimodal":[155,183,228,289,307,318,323],"(systems":[157],"consider":[159],"video":[163,285],"components).":[164],"due":[167],"difficulty":[170],"them":[173],"also":[175],"scarsity":[178],"datasets":[180,286],"containing":[181,261],"data":[184],"train":[186],"test":[188],"designed":[190],"algorithms.":[191],"In":[192],"paper":[194],"we":[195,206,248,292],"focus":[196],"an":[201],"audio-visual":[202],"deepfake":[203,214,324],"dataset.<br>":[204],"First,":[205],"present":[207,293],"general":[209],"pipeline":[210,251],"for":[211,317],"synthesizing":[212],"speech":[213,245,259],"from":[216],"given":[218],"real":[219],"or":[220,279],"video,":[222],"facilitating":[223],"creation":[225],"counterfeit":[227],"material.":[229],"proposed":[231,299],"method":[232],"uses":[233],"Text-to-Speech":[234],"(TTS)":[235],"Dynamic":[237],"Time":[238],"Warping":[239],"(DTW)":[240],"techniques":[241],"achieve":[243],"realistic":[244],"tracks.":[246],"Then,":[247],"use":[249],"generate":[253],"release":[255],"TIMIT-TTS,":[256],"synthetic":[258],"dataset":[260,300],"cutting-edge":[264],"methods":[265],"TTS":[268],"field.":[269],"used":[273],"standalone":[276],"dataset,":[278],"combined":[280],"DeepfakeTIMIT":[282],"VidTIMIT":[284],"perform":[288],"research.":[290],"Finally,":[291],"numerous":[294],"experiments":[295],"benchmark":[297],"(i.e.,":[304,308],"audio)":[305],"video)":[311],"conditions.<br>":[312],"highlights":[314],"need":[316],"data.":[325],"For":[326],"initial":[328],"version":[329],"TIMIT-TTS":[331,335],"<strong>v1.0</strong>":[332],"Arxiv:":[333],"https://arxiv.org/abs/2209.08000":[334],"Database":[336],"v1.0:":[337],"https://zenodo.org/record/6560159":[338]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
