{"id":"https://openalex.org/W2788830260","doi":"https://doi.org/10.1109/icassp.2018.8462018","title":"Voice Impersonation Using Generative Adversarial Networks","display_name":"Voice Impersonation Using Generative Adversarial Networks","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2788830260","doi":"https://doi.org/10.1109/icassp.2018.8462018","mag":"2788830260"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/1802.06840","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102873084","display_name":"Yang Gao","orcid":"https://orcid.org/0000-0003-0348-2546"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yang Gao","raw_affiliation_strings":["Electrical and Computer Engineering Department, Carnegie Mellon University","[Electrical and Computer Engineering Department, Carnegie Mellon University]"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"[Electrical and Computer Engineering Department, Carnegie Mellon University]","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102775511","display_name":"Rita Singh","orcid":"https://orcid.org/0000-0003-3743-0162"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rita Singh","raw_affiliation_strings":["Schmidt Sciences, Palo Alto, CA","[Electrical and Computer Engineering Department, Carnegie Mellon University]"],"affiliations":[{"raw_affiliation_string":"Schmidt Sciences, Palo Alto, CA","institution_ids":[]},{"raw_affiliation_string":"[Electrical and Computer Engineering Department, Carnegie Mellon University]","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113017615","display_name":"Bhiksha Raj","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhiksha Raj","raw_affiliation_strings":["Electrical and Computer Engineering Department, Carnegie Mellon University","[Electrical and Computer Engineering Department, Carnegie Mellon University]"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"[Electrical and Computer Engineering Department, Carnegie Mellon University]","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102873084"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":1.87697301,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.85519635,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2506","last_page":"2510"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9991000294685364,"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":0.9987999796867371,"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":0.9975000023841858,"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/spectrogram","display_name":"Spectrogram","score":0.7756413221359253},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.691459059715271},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6472442746162415},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5680695176124573},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5257942080497742},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5193961262702942},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5104357600212097},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.500385046005249},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.47512274980545044},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4646240174770355},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33251631259918213},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3297857940196991}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7756413221359253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.691459059715271},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6472442746162415},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5680695176124573},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5257942080497742},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5193961262702942},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5104357600212097},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.500385046005249},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.47512274980545044},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4646240174770355},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33251631259918213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3297857940196991},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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":4,"locations":[{"id":"doi:10.1109/icassp.2018.8462018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1802.06840","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1802.06840","pdf_url":"https://arxiv.org/pdf/1802.06840","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":"","raw_type":"text"},{"id":"mag:2788830260","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1802.06840","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":"doi:10.48550/arxiv.1802.06840","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1802.06840","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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1802.06840","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1802.06840","pdf_url":"https://arxiv.org/pdf/1802.06840","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":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2788830260.pdf","grobid_xml":"https://content.openalex.org/works/W2788830260.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1574170747","https://openalex.org/W1921523184","https://openalex.org/W1963778986","https://openalex.org/W2013996527","https://openalex.org/W2032074738","https://openalex.org/W2086796102","https://openalex.org/W2120605154","https://openalex.org/W2120847449","https://openalex.org/W2159035631","https://openalex.org/W2165674530","https://openalex.org/W2173520492","https://openalex.org/W2475287302","https://openalex.org/W2605287558","https://openalex.org/W2703190149","https://openalex.org/W2949117887","https://openalex.org/W2951939904","https://openalex.org/W2962793481","https://openalex.org/W2962947361","https://openalex.org/W6634468015","https://openalex.org/W6638667902","https://openalex.org/W6683225834"],"related_works":["https://openalex.org/W2964135678","https://openalex.org/W2608338293","https://openalex.org/W2125389028","https://openalex.org/W3137768380","https://openalex.org/W2962793481","https://openalex.org/W2951004968","https://openalex.org/W2805669069","https://openalex.org/W2099471712","https://openalex.org/W2032928894","https://openalex.org/W3199506689","https://openalex.org/W2972659941","https://openalex.org/W2970903655","https://openalex.org/W3012498027","https://openalex.org/W2258901759","https://openalex.org/W2945162702","https://openalex.org/W2937077299","https://openalex.org/W3011197176","https://openalex.org/W3163320179","https://openalex.org/W3185520669","https://openalex.org/W2749804538"],"abstract_inverted_index":{"Voice":[0],"impersonation":[1],"is":[2,12,80,130,181],"not":[3,39],"the":[4,10,21,27,35,41,50,53,73,100,105,114,126,133,141,149,159,170],"same":[5],"as":[6,148],"voice":[7,19,23,108],"transformation,":[8],"although":[9],"latter":[11],"an":[13],"essential":[14],"element":[15],"of":[16,29,52,75,94,113,117,144,151,161,164,177],"it.":[17],"In":[18,56,136],"impersonation,":[20],"resultant":[22],"must":[24],"convincingly":[25],"convey":[26],"impression":[28],"having":[30],"been":[31],"naturally":[32],"produced":[33],"by":[34],"target":[36,54,97,106],"speaker,":[37],"mimicking":[38],"only":[40],"pitch":[42],"and":[43,68,85,96,110],"other":[44],"perceivable":[45],"signal":[46,129],"qualities,":[47],"but":[48],"also":[49],"style":[51],"speaker.":[55],"this":[57,138],"paper,":[58],"we":[59],"propose":[60],"a":[61,83,121],"novel":[62],"neural":[63],"network":[64,89],"based":[65],"speech":[66,154,165],"quality-":[67],"style-":[69],"mimicry":[70],"framework":[71,79],"for":[72,146,153,198],"synthesis":[74],"impersonated":[76,178],"voices.":[77,201],"The":[78],"built":[81],"upon":[82],"fast":[84],"accurate":[86],"generative":[87],"adversarial":[88],"model.":[90],"Given":[91],"spectrographic":[92],"representations":[93],"source":[95],"speakers'":[98],"voices,":[99],"model":[101,139,171],"learns":[102],"to":[103,184],"mimic":[104],"speaker's":[107],"quality":[109],"style,":[111],"regardless":[112],"linguistic":[115],"content":[116],"either's":[118],"voice,":[119],"generating":[120],"synthetic":[122],"spectrogram":[123],"from":[124],"which":[125],"time":[127],"domain":[128],"reconstructed":[131],"using":[132,195],"Griffin-Lim":[134],"method.":[135],"effect,":[137],"reframes":[140],"well-known":[142],"problem":[143,150,160],"style-transfer":[145,152],"images":[147],"signals,":[155],"while":[156],"intrinsically":[157],"addressing":[158],"durational":[162],"variability":[163],"sounds.":[166],"Experiments":[167],"demonstrate":[168],"that":[169],"can":[172],"generate":[173],"extremely":[174],"convincing":[175],"samples":[176],"speech.":[179],"It":[180],"even":[182],"able":[183],"impersonate":[185],"voices":[186],"across":[187],"different":[188],"genders":[189],"effectively.":[190],"Results":[191],"are":[192],"qualitatively":[193],"evaluated":[194],"standard":[196],"procedures":[197],"evaluating":[199],"synthesized":[200]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}