{"id":"https://openalex.org/W2963192573","doi":"https://doi.org/10.48550/arxiv.1802.06006","title":"Neural Voice Cloning with a Few Samples","display_name":"Neural Voice Cloning with a Few Samples","publication_year":2018,"publication_date":"2018-02-14","ids":{"openalex":"https://openalex.org/W2963192573","doi":"https://doi.org/10.48550/arxiv.1802.06006","mag":"2963192573"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1802.06006","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1802.06006","pdf_url":"https://arxiv.org/pdf/1802.06006","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1802.06006","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037420650","display_name":"Sercan \u00d6. Ar\u0131k","orcid":"https://orcid.org/0000-0001-6333-1729","observed_orcids":["https://orcid.org/0000-0001-6333-1729"]},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Arik, Sercan O.","raw_affiliation_strings":["Baidu (China), Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu (China), Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046063537","display_name":"Jitong Chen","orcid":"https://orcid.org/0000-0001-6084-043X","observed_orcids":["https://orcid.org/0000-0001-6084-043X"]},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Jitong","raw_affiliation_strings":["Baidu Research 1195 Bordeaux Dr. Sunnyvale , CA 94089","Baidu (China), Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Research 1195 Bordeaux Dr. Sunnyvale , CA 94089","institution_ids":["https://openalex.org/I98301712"]},{"raw_affiliation_string":"Baidu (China), Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052554838","display_name":"Kainan Peng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng, Kainan","raw_affiliation_strings":["Baidu Research 1195 Bordeaux Dr. Sunnyvale , CA 94089","Baidu (China), Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Research 1195 Bordeaux Dr. Sunnyvale , CA 94089","institution_ids":["https://openalex.org/I98301712"]},{"raw_affiliation_string":"Baidu (China), Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113987537","display_name":"Wei Ping","orcid":"https://orcid.org/0000-0002-8852-6618","observed_orcids":["https://orcid.org/0000-0002-8852-6618"]},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping, Wei","raw_affiliation_strings":["Baidu Research 1195 Bordeaux Dr. Sunnyvale , CA 94089","Baidu (China), Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Research 1195 Bordeaux Dr. Sunnyvale , CA 94089","institution_ids":["https://openalex.org/I98301712"]},{"raw_affiliation_string":"Baidu (China), Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081567725","display_name":"Yanqi Zhou","orcid":"https://orcid.org/0000-0003-2051-7616","observed_orcids":["https://orcid.org/0000-0003-2051-7616","https://orcid.org/0009-0003-9304-6090"]},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou, Yanqi","raw_affiliation_strings":["Baidu Research 1195 Bordeaux Dr. Sunnyvale , CA 94089","Baidu (China), Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Research 1195 Bordeaux Dr. Sunnyvale , CA 94089","institution_ids":["https://openalex.org/I98301712"]},{"raw_affiliation_string":"Baidu (China), Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98301712"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":309,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"31","issue":null,"first_page":"10019","last_page":"10029"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":9.999999747378752e-05,"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/T10863","display_name":"Voice and Speech Disorders","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/voice-cloning","display_name":"voice cloning","score":0.7919999957084656},{"id":"https://openalex.org/keywords/speaker-adaptation","display_name":"speaker adaptation","score":0.8050000071525574},{"id":"https://openalex.org/keywords/multi-speaker-speech-synthesis","display_name":"multi-speaker speech synthesis","score":0.7850000262260437},{"id":"https://openalex.org/keywords/speaker-embedding","display_name":"speaker embedding","score":0.6499999761581421},{"id":"https://openalex.org/keywords/speech-naturalness","display_name":"speech naturalness","score":0.718999981880188},{"id":"https://openalex.org/keywords/low-resource-deployment","display_name":"low-resource deployment","score":0.9010000228881836}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8503232002258301},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.771866500377655},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.7595139741897583},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7374132871627808},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5977860689163208},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5611243844032288},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4745515286922455},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.465490460395813},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4498887062072754},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4489648640155792},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.44504404067993164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38397759199142456},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2813641428947449},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10211366415023804},{"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/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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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":3,"locations":[{"id":"pmh:oai:arXiv.org:1802.06006","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1802.06006","pdf_url":"https://arxiv.org/pdf/1802.06006","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1802.06006","doi":"https://doi.org/10.48550/arxiv.1802.06006","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1802.06006","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:2963192573","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/2018/file/4559912e7a94a9c32b09d894f2bc3c82-Paper.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1802.06006","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1802.06006","pdf_url":"https://arxiv.org/pdf/1802.06006","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963192573.pdf","grobid_xml":"https://content.openalex.org/works/W2963192573.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W2048526313","https://openalex.org/W2086796102","https://openalex.org/W2112021726","https://openalex.org/W2114168642","https://openalex.org/W2121812409","https://openalex.org/W2129142580","https://openalex.org/W2153914468","https://openalex.org/W2193413348","https://openalex.org/W2194321275","https://openalex.org/W2198484938","https://openalex.org/W2259472270","https://openalex.org/W2317898072","https://openalex.org/W2401812832","https://openalex.org/W2401822949","https://openalex.org/W2408712009","https://openalex.org/W2512087624","https://openalex.org/W2515028311","https://openalex.org/W2519091744","https://openalex.org/W2527729766","https://openalex.org/W2584032004","https://openalex.org/W2587150483","https://openalex.org/W2591927543","https://openalex.org/W2604184139","https://openalex.org/W2605320104","https://openalex.org/W2606176153","https://openalex.org/W2612434969","https://openalex.org/W2626778328","https://openalex.org/W2736900972","https://openalex.org/W2743945814","https://openalex.org/W2766527293","https://openalex.org/W2766669584","https://openalex.org/W2766812927","https://openalex.org/W2774796173","https://openalex.org/W2901997113","https://openalex.org/W2949247522","https://openalex.org/W2963381607","https://openalex.org/W2963636093","https://openalex.org/W2963712897","https://openalex.org/W2964243274"],"related_works":["https://openalex.org/W6925244429","https://openalex.org/W4403262828","https://openalex.org/W4285301843","https://openalex.org/W7165588396","https://openalex.org/W4402696814","https://openalex.org/W4401314792","https://openalex.org/W4385993834","https://openalex.org/W3034373943","https://openalex.org/W7219489998","https://openalex.org/W4389363808"],"abstract_inverted_index":{"Voice":[0],"cloning":[1,38,70,89,123,135],"is":[2,59,74,145],"a":[3,25,35,42,63,68,78,84,96],"highly":[4],"desired":[5],"feature":[6],"for":[7,24,140,151],"personalized":[8],"speech":[9,14,23,106],"interfaces.":[10],"Neural":[11],"network":[12],"based":[13,60,75],"synthesis":[15],"has":[16],"been":[17],"shown":[18],"to":[19,81,92,110],"generate":[20],"high":[21],"quality":[22],"large":[26],"number":[27],"of":[28,102,104],"speakers.":[29],"In":[30,100],"this":[31],"paper,":[32],"we":[33],"introduce":[34],"neural":[36],"voice":[37],"system":[39],"that":[40],"takes":[41],"few":[43,69,122],"audio":[44],"samples":[45],"as":[46],"input.":[47],"We":[48],"study":[49],"two":[50],"approaches:":[51],"speaker":[52,55,86,126,142],"adaptation":[53,58,127],"and":[54,91,107,132],"encoding.":[56],"Speaker":[57,72],"on":[61,76],"fine-tuning":[62],"multi-speaker":[64,97],"generative":[65,98],"model":[66,80],"with":[67,95,120],"samples.":[71],"encoding":[73,143],"training":[77],"separate":[79],"directly":[82],"infer":[83],"new":[85],"embedding":[87],"from":[88],"audios":[90],"be":[93],"used":[94],"model.":[99],"terms":[101],"naturalness":[103,131],"the":[105,134,141],"its":[108],"similarity":[109],"original":[111],"speaker,":[112],"both":[113],"approaches":[114],"can":[115,128],"achieve":[116,129],"good":[117],"performance,":[118],"even":[119],"very":[121],"audios.":[124],"While":[125],"better":[130],"similarity,":[133],"time":[136],"or":[137],"required":[138],"memory":[139],"approach":[144],"significantly":[146],"less,":[147],"making":[148],"it":[149],"favorable":[150],"low-resource":[152],"deployment.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":33},{"year":2023,"cited_by_count":28},{"year":2022,"cited_by_count":57},{"year":2021,"cited_by_count":61},{"year":2020,"cited_by_count":48},{"year":2019,"cited_by_count":42},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2019-07-30T00:00:00"}