{"id":"https://openalex.org/W4296068758","doi":"https://doi.org/10.21437/interspeech.2022-367","title":"CopyCat2: A Single Model for Multi-Speaker TTS and Many-to-Many Fine-Grained Prosody Transfer","display_name":"CopyCat2: A Single Model for Multi-Speaker TTS and Many-to-Many Fine-Grained Prosody Transfer","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296068758","doi":"https://doi.org/10.21437/interspeech.2022-367"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-367","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-367","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","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/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":["Alexa AI, Amazon, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI, Amazon, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006537074","display_name":"Penny Karanasou","orcid":"https://orcid.org/0000-0003-1939-4161"},"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":"Penny Karanasou","raw_affiliation_strings":["Alexa AI, Amazon, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI, Amazon, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032468476","display_name":"Mateusz \u0141ajszczak","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":"Mateusz \u0141ajszczak","raw_affiliation_strings":["Alexa AI, Amazon, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI, Amazon, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069384071","display_name":"Syed Ammar Abbas","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":"Syed Ammar Abbas","raw_affiliation_strings":["Alexa AI, Amazon, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI, Amazon, 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":["Alexa AI, Amazon, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI, Amazon, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089340248","display_name":"Peter Makarov","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":"Peter Makarov","raw_affiliation_strings":["Alexa AI, Amazon, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI, Amazon, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077120267","display_name":"Ray Li","orcid":"https://orcid.org/0000-0003-3441-2364"},"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":"Ray Li","raw_affiliation_strings":["Alexa AI, Amazon, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI, Amazon, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004739281","display_name":"Arent van Korlaar","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":"Arent van Korlaar","raw_affiliation_strings":["Alexa AI, Amazon, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI, Amazon, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021062762","display_name":"Simon Slangen","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":"Simon Slangen","raw_affiliation_strings":["Alexa AI, Amazon, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI, Amazon, 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":["Alexa AI, Amazon, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI, Amazon, 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":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3363","last_page":"3367"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.996399998664856,"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/T12031","display_name":"Speech and dialogue systems","score":0.9929999709129333,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.8226526975631714},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7324970960617065},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.557535707950592},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4623950719833374},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3356444835662842}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8226526975631714},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7324970960617065},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.557535707950592},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4623950719833374},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3356444835662842},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-367","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-367","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2069859485","https://openalex.org/W2188365844","https://openalex.org/W2794490148","https://openalex.org/W2896457183","https://openalex.org/W2903739847","https://openalex.org/W2904459034","https://openalex.org/W2950821630","https://openalex.org/W2954386831","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W2973158936","https://openalex.org/W2973217961","https://openalex.org/W2990883660","https://openalex.org/W3015282541","https://openalex.org/W3022876224","https://openalex.org/W3026874504","https://openalex.org/W3096634037","https://openalex.org/W3097538987","https://openalex.org/W3118485687","https://openalex.org/W3161113899","https://openalex.org/W3162770051","https://openalex.org/W3172148458","https://openalex.org/W3197957589","https://openalex.org/W3198213150","https://openalex.org/W3200540417","https://openalex.org/W4221167022","https://openalex.org/W4286950013","https://openalex.org/W4287121924"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2355553914","https://openalex.org/W149862513","https://openalex.org/W2347684782","https://openalex.org/W4320472397","https://openalex.org/W2401269021","https://openalex.org/W2145654520","https://openalex.org/W2750037515","https://openalex.org/W4319862652"],"abstract_inverted_index":{"In":[0],"this":[1,42],"paper,":[2],"we":[3,84],"present":[4],"CopyCat2":[5],"(CC2),":[6],"a":[7,57,144],"novel":[8,58],"model":[9,55,66],"capable":[10],"of:":[11],"a)":[12],"synthesizing":[13],"speech":[14,21,73,135],"with":[15,22,102,115],"different":[16,51],"speaker":[17,151],"identities,":[18],"b)":[19],"generating":[20],"expressive":[23],"and":[24,28,119,133],"contextually":[25,103,116],"appropriate":[26,104,117],"prosody,":[27,118],"c)":[29],"transferring":[30],"prosody":[31,70,80,89,123,139],"at":[32],"fine-grained":[33,122,138],"level":[34],"between":[35,130],"any":[36],"pair":[37],"of":[38,47,147],"seen":[39],"speakers.We":[40],"do":[41],"by":[43,136],"activating":[44],"distinct":[45],"parts":[46],"the":[48,65,92,126],"network":[49],"for":[50,77],"tasks.We":[52],"train":[53],"our":[54,131],"using":[56,91],"approach":[59],"to":[60,86,108],"two-stage":[61],"training.In":[62],"Stage":[63,82],"I,":[64],"learns":[67],"speaker-independent":[68],"word-level":[69],"representations":[71,90],"from":[72],"which":[74],"it":[75,142],"uses":[76],"many-to-many":[78],"finegrained":[79],"transfer.In":[81],"II,":[83],"learn":[85],"predict":[87],"these":[88],"contextual":[93],"information":[94],"available":[95],"in":[96,113,121,128,149],"text,":[97],"thereby,":[98],"enabling":[99],"multi-speaker":[100],"TTS":[101,114],"prosody.We":[105],"compare":[106],"CC2":[107],"two":[109],"strong":[110],"baselines,":[111],"one":[112,120],"transfer.CC2":[124],"reduces":[125],"gap":[127],"naturalness":[129],"baseline":[132],"copy-synthesised":[134],"22.79%.In":[137],"transfer":[140],"evaluations,":[141],"obtains":[143],"relative":[145],"improvement":[146],"33.15%":[148],"target":[150],"similarity.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
