{"id":"https://openalex.org/W2791178280","doi":"https://doi.org/10.21437/odyssey.2018-34","title":"Can we steal your vocal identity from the Internet?: Initial investigation of cloning Obama\u2019s voice using GAN, WaveNet and low-quality found data","display_name":"Can we steal your vocal identity from the Internet?: Initial investigation of cloning Obama\u2019s voice using GAN, WaveNet and low-quality found data","publication_year":2018,"publication_date":"2018-06-06","ids":{"openalex":"https://openalex.org/W2791178280","doi":"https://doi.org/10.21437/odyssey.2018-34","mag":"2791178280"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2018-34","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2018-34","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2018)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1803.00860","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019530089","display_name":"Jaime Lorenzo-Trueba","orcid":"https://orcid.org/0000-0003-0459-1429"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jaime Lorenzo-Trueba","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012466506","display_name":"Fuming Fang","orcid":"https://orcid.org/0000-0002-9332-3735"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fuming Fang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327839","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0001-8246-0606"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044556342","display_name":"Isao Echizen","orcid":"https://orcid.org/0000-0003-4908-1860"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Isao Echizen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5043168931","display_name":"Tomi Kinnunen","orcid":"https://orcid.org/0000-0002-4371-7322"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomi Kinnunen","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5019530089"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0307,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.89652479,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"240","last_page":"247"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.998199999332428,"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/T11309","display_name":"Music and Audio Processing","score":0.9962000250816345,"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/naturalness","display_name":"Naturalness","score":0.8486883640289307},{"id":"https://openalex.org/keywords/spoofing-attack","display_name":"Spoofing attack","score":0.7562577128410339},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.750945508480072},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6384305357933044},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5379515290260315},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4506075084209442},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.42218726873397827},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.12891241908073425}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8486883640289307},{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.7562577128410339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.750945508480072},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6384305357933044},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5379515290260315},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4506075084209442},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.42218726873397827},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.12891241908073425},{"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},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.21437/odyssey.2018-34","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2018-34","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2018)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1803.00860","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.00860","pdf_url":"https://arxiv.org/pdf/1803.00860","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2791178280","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1803.00860.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:pure.ed.ac.uk:openaire/b0f8d0d2-a1af-4a92-9c55-fe720428365c","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/b0f8d0d2-a1af-4a92-9c55-fe720428365c","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lorenzo-Trueba, J, Fang, F, Wang, X, Echizen, I, Yamagishi, J & Kinnunen, T 2018, Can we steal your vocal identity from the Internet?: Initial investigation of cloning Obama\u2019s voice using GAN, WaveNet and low-quality found data. in Speaker Odyssey 2018 : The Speaker and Language Recognition Workshop. Les Sables d\u2019Olonne, France, pp. 240-247, The Speaker and Language Recognition Workshop, Les Sables d\u2019Olonne, France, 26/06/18. https://doi.org/10.21437/Odyssey.2018-34","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/b0f8d0d2-a1af-4a92-9c55-fe720428365c","is_oa":true,"landing_page_url":"https://www.isca-speech.org/archive/Odyssey_2018/abstracts/48.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":"Lorenzo-Trueba, J, Fang, F, Wang, X, Echizen, I, Yamagishi, J & Kinnunen, T 2018, Can we steal your vocal identity from the Internet?: Initial investigation of cloning Obama\u2019s voice using GAN, WaveNet and low-quality found data. in Speaker Odyssey 2018 : The Speaker and Language Recognition Workshop. Les Sables d\u2019Olonne, France, pp. 240-247, The Speaker and Language Recognition Workshop, Les Sables d\u2019Olonne, France, 26/06/18. https://doi.org/10.21437/Odyssey.2018-34","raw_type":"contributionToPeriodical"},{"id":"doi:10.48550/arxiv.1803.00860","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1803.00860","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1803.00860","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.00860","pdf_url":"https://arxiv.org/pdf/1803.00860","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W304834817","https://openalex.org/W2094721231","https://openalex.org/W2144561273","https://openalex.org/W2409959948","https://openalex.org/W2514828952","https://openalex.org/W2588445447","https://openalex.org/W2593414223","https://openalex.org/W2600556233","https://openalex.org/W2603567530","https://openalex.org/W2666408839","https://openalex.org/W2738359832","https://openalex.org/W2738406145","https://openalex.org/W2747914378","https://openalex.org/W2749651610","https://openalex.org/W2762101354","https://openalex.org/W2782422271","https://openalex.org/W2782892391","https://openalex.org/W2949117887","https://openalex.org/W2949382160","https://openalex.org/W2949888546","https://openalex.org/W2950304420","https://openalex.org/W2962793481","https://openalex.org/W2963321191","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W3126437110"],"related_works":["https://openalex.org/W2964195110","https://openalex.org/W2608338293","https://openalex.org/W3024837596","https://openalex.org/W3203614938","https://openalex.org/W2095219843","https://openalex.org/W3194822862","https://openalex.org/W174657792","https://openalex.org/W2796771987","https://openalex.org/W3102396314","https://openalex.org/W1550959190","https://openalex.org/W2251498782","https://openalex.org/W3167732619","https://openalex.org/W2546627663","https://openalex.org/W3076645148","https://openalex.org/W1980988531","https://openalex.org/W2465492956","https://openalex.org/W3169409951","https://openalex.org/W2796069293","https://openalex.org/W3009657206","https://openalex.org/W2898786057"],"abstract_inverted_index":{"Thanks":[0],"to":[1,30,69],"the":[2,36,51,71,96,107,134,139,155,159,165,168,171,180],"growing":[3],"availability":[4],"of":[5,73,98,123,141,158,167],"spoofing":[6,18,75],"databases":[7],"and":[8,23,26,42,62,114,118,127,150],"rapid":[9],"advances":[10],"in":[11,50,102,121,146],"using":[12,77],"them,":[13],"systems":[14,76],"for":[15,35],"detecting":[16],"voice":[17,43,115],"attacks":[19],"are":[20,32,47,54],"becoming":[21],"more":[22,24],"capable,":[25],"error":[27],"rates":[28],"close":[29],"zero":[31],"being":[33],"reached":[34],"ASVspoof2015":[37,52],"database.":[38],"However,":[39,170],"speech":[40,91,99,125,161,178],"synthesis":[41],"conversion":[44,116],"paradigms":[45],"that":[46,83,94,133,151],"not":[48],"considered":[49],"database":[53],"appearing.":[55],"Such":[56],"examples":[57],"include":[58],"direct":[59],"waveform":[60],"modelling":[61],"generative":[63,88],"adversarial":[64,89],"networks.":[65],"We":[66],"also":[67,173],"need":[68],"investigate":[70],"feasibility":[72],"training":[74],"only":[78],"low-quality":[79,142,181],"found":[80,101,145,182],"data.":[81,183],"For":[82],"purpose,":[84],"we":[85,110],"developed":[86],"a":[87],"network-based":[90],"enhancement":[92,135],"system":[93],"improves":[95],"quality":[97,126],"data":[100,144],"publicly":[103,147],"available":[104,148],"sources.":[105],"Using":[106],"enhanced":[108],"data,":[109],"trained":[111],"state-of-the-art":[112],"text-to-speech":[113],"models":[117,136],"evaluated":[119],"them":[120],"terms":[122],"perceptual":[124,156],"speaker":[128],"similarity.":[129],"The":[130],"results":[131,172],"show":[132,174],"significantly":[137,153,163],"improved":[138,154],"SNR":[140],"degraded":[143],"sources":[149],"they":[152],"cleanliness":[157],"source":[160],"without":[162],"degrading":[164],"naturalness":[166],"voice.":[169],"limitations":[175],"when":[176],"generating":[177],"with":[179]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}