{"id":"https://openalex.org/W2973045721","doi":"https://doi.org/10.21437/ssw.2019-29","title":"V2S attack: building DNN-based voice conversion from automatic speaker verification","display_name":"V2S attack: building DNN-based voice conversion from automatic speaker verification","publication_year":2019,"publication_date":"2019-09-14","ids":{"openalex":"https://openalex.org/W2973045721","doi":"https://doi.org/10.21437/ssw.2019-29","mag":"2973045721"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2019-29","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2019-29","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"10th ISCA Workshop on Speech Synthesis (SSW 10)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104139092","display_name":"Taiki Nakamura","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Taiki Nakamura","raw_affiliation_strings":["Faculty of Engineering, The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083394213","display_name":"Yuki Saito","orcid":"https://orcid.org/0000-0002-7967-2613"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Saito","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinnosuke Takamichi","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068604686","display_name":"Yusuke Ijima","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Ijima","raw_affiliation_strings":["Nippon Telegraph and Telephone Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"Nippon Telegraph and Telephone Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003814223","display_name":"Hiroshi Saruwatari","orcid":"https://orcid.org/0000-0003-0876-5617"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Saruwatari","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5104139092"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.5601,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75212889,"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":"161","last_page":"165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9973000288009644,"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":0.9968000054359436,"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/computer-science","display_name":"Computer science","score":0.7990469336509705},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7322877645492554},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6894165277481079},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.628706693649292},{"id":"https://openalex.org/keywords/authentication","display_name":"Authentication (law)","score":0.5654163956642151},{"id":"https://openalex.org/keywords/biometrics","display_name":"Biometrics","score":0.5055618286132812},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4896436333656311},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4234622120857239},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25065532326698303},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.13272827863693237}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7990469336509705},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7322877645492554},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6894165277481079},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.628706693649292},{"id":"https://openalex.org/C148417208","wikidata":"https://www.wikidata.org/wiki/Q4825882","display_name":"Authentication (law)","level":2,"score":0.5654163956642151},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.5055618286132812},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4896436333656311},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4234622120857239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25065532326698303},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.13272827863693237},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/ssw.2019-29","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2019-29","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"10th ISCA Workshop on Speech Synthesis (SSW 10)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4099999964237213,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322525","display_name":"Secom Science and Technology Foundation","ror":"https://ror.org/05ggzej07"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1485222997","https://openalex.org/W1604510059","https://openalex.org/W1665214252","https://openalex.org/W1945616565","https://openalex.org/W1959608418","https://openalex.org/W2046056978","https://openalex.org/W2049686551","https://openalex.org/W2072473772","https://openalex.org/W2120605154","https://openalex.org/W2126143605","https://openalex.org/W2146502635","https://openalex.org/W2150769028","https://openalex.org/W2156142001","https://openalex.org/W2518172956","https://openalex.org/W2519091744","https://openalex.org/W2696558042","https://openalex.org/W2787051072","https://openalex.org/W2787253006","https://openalex.org/W2808706139","https://openalex.org/W2898435086","https://openalex.org/W2936473415","https://openalex.org/W2949558265","https://openalex.org/W2963403664","https://openalex.org/W2963971656","https://openalex.org/W4289299396","https://openalex.org/W4320013936"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W3104966193","https://openalex.org/W1521299571","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W4235705411","https://openalex.org/W1493012537","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,46,51,165],"new":[4],"voice":[5,9,34,91,112,138,171],"impersonation":[6],"attack":[7],"using":[8,164],"conversion":[10],"(VC).Enrolling":[11],"personal":[12],"voices":[13,126],"for":[14],"automatic":[15,81],"speaker":[16],"verification":[17],"(ASV)":[18],"offers":[19],"natural":[20],"and":[21,43,72,79,86,105,140],"flexible":[22],"biometric":[23],"authentication":[24],"systems.Basically,":[25],"the":[26,32,37,54,62,68,77,88,96,102,119,128,135,141,146,152,158],"ASV":[27,38,78,103],"systems":[28],"do":[29],"not":[30,133],"include":[31],"users'":[33],"data.However,":[35],"if":[36],"system":[39],"is":[40,50],"unexpectedly":[41],"exposed":[42],"hacked":[44],"by":[45,100,113,118],"malicious":[47],"attacker,":[48],"there":[49],"risk":[52],"that":[53,131,144,151,162],"attacker":[55],"will":[56],"use":[57,134],"VC":[58,74,93,143,160],"techniques":[59],"to":[60,157],"reproduce":[61],"enrolled":[63],"user's":[64],"voices.We":[65],"name":[66],"this":[67],"\"verificationto-synthesis":[69],"(V2S)":[70],"attack\"":[71],"propose":[73],"training":[75],"with":[76],"pre-trained":[80],"speech":[82],"recognition":[83],"(ASR)":[84],"models":[85],"without":[87],"targeted":[89,97,136],"speaker's":[90,98,137],"data.The":[92,147],"model":[94,104],"reproduces":[95],"individuality":[99],"deceiving":[101],"restores":[106],"phonetic":[107,115],"property":[108],"of":[109,169],"an":[110],"input":[111],"matching":[114],"posteriorgrams":[116],"predicted":[117],"ASR":[120],"model.The":[121],"experimental":[122,148],"evaluation":[123],"compares":[124],"converted":[125],"between":[127],"proposed":[129,153],"method":[130,154],"does":[132],"data":[139],"standard":[142],"uses":[145],"results":[149],"demonstrate":[150],"performs":[155],"comparably":[156],"existing":[159],"methods":[161],"trained":[163],"very":[166],"small":[167],"amount":[168],"parallel":[170],"data.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
