{"id":"https://openalex.org/W4291289691","doi":"https://doi.org/10.48550/arxiv.2111.12277","title":"One-shot Voice Conversion For Style Transfer Based On Speaker Adaptation","display_name":"One-shot Voice Conversion For Style Transfer Based On Speaker Adaptation","publication_year":2021,"publication_date":"2021-11-24","ids":{"openalex":"https://openalex.org/W4291289691","doi":"https://doi.org/10.48550/arxiv.2111.12277"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2111.12277","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.12277","pdf_url":"https://arxiv.org/pdf/2111.12277","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2111.12277","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106698700","display_name":"Zhichao Wang","orcid":"https://orcid.org/0000-0001-8075-1784","observed_orcids":["https://orcid.org/0000-0001-8075-1784","https://orcid.org/0009-0003-7473-3143"]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Zhichao","raw_affiliation_strings":["Audio , Speech and Language Processing Group (ASLP@NPU) School of Computer Science , Northwestern Polytechnical University , Xi'an , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio , Speech and Language Processing Group (ASLP@NPU) School of Computer Science , Northwestern Polytechnical University , Xi'an , China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049213273","display_name":"Qicong Xie","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie, Qicong","raw_affiliation_strings":["Audio , Speech and Language Processing Group (ASLP@NPU) School of Computer Science , Northwestern Polytechnical University , Xi'an , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio , Speech and Language Processing Group (ASLP@NPU) School of Computer Science , Northwestern Polytechnical University , Xi'an , China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100455256","display_name":"Tao Li","orcid":"https://orcid.org/0000-0001-8966-7239","observed_orcids":["https://orcid.org/0000-0001-8966-7239"]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Tao","raw_affiliation_strings":["Audio , Speech and Language Processing Group (ASLP@NPU) School of Computer Science , Northwestern Polytechnical University , Xi'an , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio , Speech and Language Processing Group (ASLP@NPU) School of Computer Science , Northwestern Polytechnical University , Xi'an , China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100856613","display_name":"Hongqiang Du","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Du, Hongqiang","raw_affiliation_strings":["Audio , Speech and Language Processing Group (ASLP@NPU) School of Computer Science , Northwestern Polytechnical University , Xi'an , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio , Speech and Language Processing Group (ASLP@NPU) School of Computer Science , Northwestern Polytechnical University , Xi'an , China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823","observed_orcids":["https://orcid.org/0000-0001-8234-0823"]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie, Lei","raw_affiliation_strings":["Audio , Speech and Language Processing Group (ASLP@NPU) School of Computer Science , Northwestern Polytechnical University , Xi'an , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio , Speech and Language Processing Group (ASLP@NPU) School of Computer Science , Northwestern Polytechnical University , Xi'an , China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050166453","display_name":"Pengcheng Zhu","orcid":"https://orcid.org/0000-0001-9867-7041","observed_orcids":["https://orcid.org/0000-0001-9867-7041","https://orcid.org/0009-0003-2373-295X"]},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhu, Pengcheng","raw_affiliation_strings":["Fuxi AI Lab , NetEase Inc. , Hangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fuxi AI Lab , NetEase Inc. , Hangzhou , China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036369578","display_name":"Mengxiao Bi","orcid":"https://orcid.org/0009-0007-6680-481X","observed_orcids":["https://orcid.org/0009-0007-6680-481X"]},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bi, Mengxiao","raw_affiliation_strings":["Fuxi AI Lab , NetEase Inc. , Hangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fuxi AI Lab , NetEase Inc. , Hangzhou , China","institution_ids":["https://openalex.org/I4210091137"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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":0.9994999766349792,"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":0.9994999766349792,"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":0.00019999999494757503,"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/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/style-transfer","display_name":"style transfer","score":0.8740000128746033},{"id":"https://openalex.org/keywords/speaker-adaptation","display_name":"speaker adaptation","score":0.9829999804496765},{"id":"https://openalex.org/keywords/speaker-normalization","display_name":"speaker normalization","score":0.8500000238418579},{"id":"https://openalex.org/keywords/weight-regularization","display_name":"weight regularization","score":0.8610000014305115},{"id":"https://openalex.org/keywords/overfitting","display_name":"overfitting","score":0.7429999709129333},{"id":"https://openalex.org/keywords/prosody-modeling","display_name":"prosody modeling","score":0.7009999752044678},{"id":"https://openalex.org/keywords/speaker-similarity","display_name":"speaker similarity","score":0.6380000114440918},{"id":"https://openalex.org/keywords/speech-quality","display_name":"speech quality","score":0.3490000069141388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7560069561004639},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7350074052810669},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7224230170249939},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6479111313819885},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6376838684082031},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5933796167373657},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.4959147870540619},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.44233065843582153},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35982316732406616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35111767053604126},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2111.12277","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.12277","pdf_url":"https://arxiv.org/pdf/2111.12277","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.2111.12277","doi":"https://doi.org/10.48550/arxiv.2111.12277","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2111.12277","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2111.12277","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.12277","pdf_url":"https://arxiv.org/pdf/2111.12277","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/W4291289691.pdf","grobid_xml":"https://content.openalex.org/works/W4291289691.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4319862431","https://openalex.org/W4394987257","https://openalex.org/W2972659941","https://openalex.org/W7024795234","https://openalex.org/W4361791061","https://openalex.org/W3197943112","https://openalex.org/W4372266960","https://openalex.org/W3126283728","https://openalex.org/W4408356288","https://openalex.org/W4403584109"],"abstract_inverted_index":{"One-shot":[0],"style":[1,47,108,137],"transfer":[2,48,106],"is":[3,58,115,126],"a":[4,41,54,112],"challenging":[5],"task,":[6],"since":[7],"training":[8,19,92],"on":[9,35,50],"one":[10,86],"utterance":[11,87],"makes":[12],"model":[13],"extremely":[14],"easy":[15],"to":[16,18,60,79,95,109,117,128],"over-fit":[17],"data":[20],"and":[21,26,39,105,138],"causes":[22],"low":[23],"speaker":[24,51,55,90,139],"similarity":[25],"lack":[27],"of":[28,136],"expressiveness.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33,71],"build":[34],"the":[36,76,98,110,129],"recognition-synthesis":[37],"framework":[38],"propose":[40],"one-shot":[42,131],"voice":[43],"conversion":[44],"approach":[45,125,143],"for":[46],"based":[49],"adaptation.":[52],"First,":[53],"normalization":[56],"module":[57,114],"adopted":[59],"remove":[61],"speaker-related":[62],"information":[63],"in":[64,75,134],"bottleneck":[65],"features":[66],"extracted":[67],"by":[68,83],"ASR.":[69],"Second,":[70],"adopt":[72],"weight":[73],"regularization":[74],"adaptation":[77],"process":[78],"prevent":[80],"over-fitting":[81],"caused":[82],"using":[84],"only":[85],"from":[88],"target":[89],"as":[91],"data.":[93],"Finally,":[94],"comprehensively":[96],"decouple":[97],"speech":[99,147],"factors,":[100],"i.e.,":[101],"content,":[102],"speaker,":[103],"style,":[104],"source":[107],"target,":[111],"prosody":[113,119],"used":[116],"extract":[118],"representation.":[120],"Experiments":[121],"show":[122],"that":[123],"our":[124,142],"superior":[127],"state-of-the-art":[130],"VC":[132],"systems":[133],"terms":[135],"similarity;":[140],"additionally,":[141],"also":[144],"maintains":[145],"good":[146],"quality.":[148]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2022-08-14T00:00:00"}
