{"id":"https://openalex.org/W3022876224","doi":"https://doi.org/10.21437/interspeech.2020-1251","title":"CopyCat: Many-to-Many Fine-Grained Prosody Transfer for Neural Text-to-Speech","display_name":"CopyCat: Many-to-Many Fine-Grained Prosody Transfer for Neural Text-to-Speech","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3022876224","doi":"https://doi.org/10.21437/interspeech.2020-1251","mag":"3022876224"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1251","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.14617","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066855316","display_name":"Sri Karlapati","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123934","display_name":"Amazon (United Kingdom)","ror":"https://ror.org/02xey9634","country_code":"GB","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210123934"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sri Karlapati","raw_affiliation_strings":["Amazon Research, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Research, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014483986","display_name":"Alexis Moinet","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123934","display_name":"Amazon (United Kingdom)","ror":"https://ror.org/02xey9634","country_code":"GB","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210123934"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alexis Moinet","raw_affiliation_strings":["Amazon Research, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Research, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083043476","display_name":"Arnaud Joly","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123934","display_name":"Amazon (United Kingdom)","ror":"https://ror.org/02xey9634","country_code":"GB","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210123934"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Arnaud Joly","raw_affiliation_strings":["Amazon Research, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Research, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026578737","display_name":"Viacheslav Klimkov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123934","display_name":"Amazon (United Kingdom)","ror":"https://ror.org/02xey9634","country_code":"GB","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210123934"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Viacheslav Klimkov","raw_affiliation_strings":["Amazon Research, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Research, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087232606","display_name":"Daniel S\u00e1ez-Trigueros","orcid":"https://orcid.org/0000-0001-9623-7472"},"institutions":[{"id":"https://openalex.org/I4210123934","display_name":"Amazon (United Kingdom)","ror":"https://ror.org/02xey9634","country_code":"GB","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210123934"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Daniel S\u00e1ez-Trigueros","raw_affiliation_strings":["Amazon Research, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Research, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029023520","display_name":"Thomas Drugman","orcid":"https://orcid.org/0000-0002-1491-7878"},"institutions":[{"id":"https://openalex.org/I4210123934","display_name":"Amazon (United Kingdom)","ror":"https://ror.org/02xey9634","country_code":"GB","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210123934"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Drugman","raw_affiliation_strings":["Amazon Research, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Research, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210123934"],"apc_list":null,"apc_paid":null,"fwci":5.9799,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.97120814,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4387","last_page":"4391"},"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":0.9940999746322632,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.8329106569290161},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7808499336242676},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7430487871170044},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7136237621307373},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5218666791915894},{"id":"https://openalex.org/keywords/copycat","display_name":"Copycat","score":0.4104588031768799},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24338948726654053}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8329106569290161},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7808499336242676},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7430487871170044},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7136237621307373},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5218666791915894},{"id":"https://openalex.org/C130191384","wikidata":"https://www.wikidata.org/wiki/Q2996887","display_name":"Copycat","level":2,"score":0.4104588031768799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24338948726654053},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2020-1251","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2004.14617","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.14617","pdf_url":"https://arxiv.org/pdf/2004.14617","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,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.14617","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.14617","pdf_url":"https://arxiv.org/pdf/2004.14617","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,"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1503398984","https://openalex.org/W1959608418","https://openalex.org/W2188365844","https://openalex.org/W2269892441","https://openalex.org/W2519091744","https://openalex.org/W2794490148","https://openalex.org/W2804078698","https://openalex.org/W2893749619","https://openalex.org/W2901997113","https://openalex.org/W2903739847","https://openalex.org/W2904459034","https://openalex.org/W2937343983","https://openalex.org/W2945478979","https://openalex.org/W2949281321","https://openalex.org/W2950821630","https://openalex.org/W2951004968","https://openalex.org/W2952716587","https://openalex.org/W2954386831","https://openalex.org/W2962691331","https://openalex.org/W2962793481","https://openalex.org/W2963272440","https://openalex.org/W2963609956","https://openalex.org/W2963927338","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2972659941","https://openalex.org/W2972951102","https://openalex.org/W2973158936","https://openalex.org/W3037695135","https://openalex.org/W4298580827","https://openalex.org/W4394668580"],"related_works":["https://openalex.org/W4392904630","https://openalex.org/W169399214","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2368768466"],"abstract_inverted_index":{"Prosody":[0],"Transfer":[1],"(PT)":[2],"is":[3,110],"a":[4,13,17,37,41,52,104,124,146,158],"technique":[5],"that":[6,109],"aims":[7,24],"to":[8,81,87,112,138],"use":[9],"the":[10,68,72,76,82,94,164,173,180],"prosody":[11,167],"from":[12,36,63],"source":[14,38,64,77,113,139],"audio":[15,39],"as":[16,79],"reference":[18,126],"while":[19,177],"synthesising":[20,49],"speech.":[21],"Fine-grained":[22],"PT":[23,61,107,149],"at":[25,40],"capturing":[26,131],"prosodic":[27,133],"aspects":[28],"like":[29],"rhythm,":[30],"emphasis,":[31],"melody,":[32],"duration,":[33],"and":[34,45,169],"loudness,":[35],"very":[42],"granular":[43],"level":[44],"transferring":[46],"them":[47],"when":[48],"speech":[50,70],"in":[51,163,171],"different":[53],"target":[54,83,174],"speaker's":[55],"voice.":[56],"Current":[57],"approaches":[58],"for":[59],"fine-grained":[60,148],"suffer":[62],"speaker":[65,78,114,140,175],"leakage,":[66,115],"where":[67,155],"synthesised":[69],"has":[71],"voice":[73],"identity":[74],"of":[75,96,130,161,166],"opposed":[80],"speaker.":[84],"In":[85,98],"order":[86],"mitigate":[88],"this":[89,99,122],"issue,":[90],"they":[91],"compromise":[92],"on":[93],"quality":[95,165],"PT.":[97],"paper,":[100],"we":[101,156],"propose":[102],"CopyCat,":[103],"novel,":[105],"many-to-many":[106],"system":[108],"robust":[111,137],"without":[116],"using":[117],"parallel":[118],"data.":[119],"We":[120,142],"achieve":[121],"through":[123,151],"novel":[125],"encoder":[127],"architecture":[128],"capable":[129],"temporal":[132],"representations":[134],"which":[135],"are":[136],"leakage.":[141],"compare":[143],"CopyCat":[144],"against":[145],"state-of-the-art":[147],"model":[150],"various":[152],"subjective":[153],"evaluations,":[154],"show":[157],"relative":[159],"improvement":[160],"$47\\%$":[162],"transfer":[168],"$14\\%$":[170],"preserving":[172],"identity,":[176],"still":[178],"maintaining":[179],"same":[181],"naturalness.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":22}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2020-05-13T00:00:00"}