{"id":"https://openalex.org/W4297841867","doi":"https://doi.org/10.21437/interspeech.2022-10761","title":"Daft-Exprt: Cross-Speaker Prosody Transfer on Any Text for Expressive Speech Synthesis","display_name":"Daft-Exprt: Cross-Speaker Prosody Transfer on Any Text for Expressive Speech Synthesis","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841867","doi":"https://doi.org/10.21437/interspeech.2022-10761"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10761","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10761","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":"article","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/A5006300453","display_name":"Julian Za\u00efdi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104072","display_name":"Ubisoft (Canada)","ror":"https://ror.org/01hmp5p66","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210104072"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Julian Za\u00efdi","raw_affiliation_strings":["Ubisoft La Forge, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ubisoft La Forge, Montreal, Canada","institution_ids":["https://openalex.org/I4210104072"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028028099","display_name":"Hugo Seut\u00e9","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104072","display_name":"Ubisoft (Canada)","ror":"https://ror.org/01hmp5p66","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210104072"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hugo Seut\u00e9","raw_affiliation_strings":["Ubisoft La Forge, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ubisoft La Forge, Montreal, Canada","institution_ids":["https://openalex.org/I4210104072"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046382731","display_name":"Benjamin van Niekerk","orcid":"https://orcid.org/0000-0001-9207-6309"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Benjamin van Niekerk","raw_affiliation_strings":["Stellenbosch University, Stellenbosch, South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stellenbosch University, Stellenbosch, South Africa","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031638419","display_name":"Marc-Andr\u00e9 Carbonneau","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104072","display_name":"Ubisoft (Canada)","ror":"https://ror.org/01hmp5p66","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210104072"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Marc-Andr\u00e9 Carbonneau","raw_affiliation_strings":["Ubisoft La Forge, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ubisoft La Forge, Montreal, Canada","institution_ids":["https://openalex.org/I4210104072"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5006300453"],"corresponding_institution_ids":["https://openalex.org/I4210104072"],"apc_list":null,"apc_paid":null,"fwci":1.9747,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.88553259,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4591","last_page":"4595"},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9966999888420105,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9950000047683716,"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/prosody","display_name":"Prosody","score":0.8063197135925293},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7421801686286926},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6210896372795105},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6142764687538147},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.5373334884643555},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.456502765417099}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8063197135925293},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7421801686286926},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6210896372795105},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6142764687538147},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.5373334884643555},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.456502765417099},{"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.2022-10761","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10761","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1882958252","https://openalex.org/W2545656684","https://openalex.org/W2567658225","https://openalex.org/W2603777577","https://openalex.org/W2760103357","https://openalex.org/W2803193013","https://openalex.org/W2903739847","https://openalex.org/W2904459034","https://openalex.org/W2932022923","https://openalex.org/W2948238043","https://openalex.org/W2954386831","https://openalex.org/W2962723986","https://openalex.org/W2963596039","https://openalex.org/W2963609956","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2972473628","https://openalex.org/W3015645837","https://openalex.org/W3022876224","https://openalex.org/W3033411150","https://openalex.org/W3091928890","https://openalex.org/W3092028330","https://openalex.org/W3094785744","https://openalex.org/W3128910262","https://openalex.org/W3150572638","https://openalex.org/W3163475957","https://openalex.org/W3168527213","https://openalex.org/W3198104520","https://openalex.org/W3201011692","https://openalex.org/W4287116966","https://openalex.org/W4289383906"],"related_works":["https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W3149582125","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W152045069","https://openalex.org/W652196294","https://openalex.org/W2368700418","https://openalex.org/W1965141925"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"Daft-Exprt,":[3],"a":[4],"multi-speaker":[5],"acoustic":[6],"model":[7,53,125],"advancing":[8],"the":[9,21,51,124,131,139],"state-of-the-art":[10,118],"for":[11,33],"cross-speaker":[12],"prosody":[13,58,95,110,132],"transfer":[14,96,111],"on":[15,107],"any":[16],"text.This":[17],"is":[18],"one":[19],"of":[20,50],"most":[22],"challenging,":[23],"and":[24,64,82,134,147],"rarely":[25],"directly":[26],"addressed,":[27],"task":[28],"in":[29,47,77],"speech":[30,137,149],"synthesis,":[31],"especially":[32],"highly":[34,78],"expressive":[35,79,119],"data.Daft-Exprt":[36],"uses":[37],"FiLM":[38],"conditioning":[39],"layers":[40],"to":[41,117],"strategically":[42],"inject":[43],"different":[44],"prosodic":[45,70,83],"information":[46,71,84,129],"all":[48],"parts":[49],"architecture.The":[52],"explicitly":[54],"encodes":[55],"traditional":[56],"low-level":[57],"features":[59],"such":[60],"as":[61],"pitch,":[62],"loudness":[63],"duration,":[65],"but":[66],"also":[67],"higher":[68],"level":[69],"that":[72,92,101,123],"helps":[73],"generating":[74],"convincing":[75],"voices":[76],"styles.Speaker":[80],"identity":[81,128],"are":[85],"disentangled":[86],"through":[87],"an":[88],"adversarial":[89],"training":[90],"strategy":[91],"enables":[93],"accurate":[94],"across":[97],"speakers.Experimental":[98],"results":[99,121],"show":[100],"Daft-Exprt":[102],"significantly":[103],"outperforms":[104],"strong":[105],"baselines":[106],"inter-text":[108],"crossspeaker":[109],"tasks,":[112],"while":[113],"yielding":[114],"naturalness":[115],"comparable":[116],"models.Moreover,":[120],"indicate":[122],"discards":[126],"speaker":[127],"from":[130,151],"representation,":[133],"consistently":[135],"generate":[136],"with":[138],"desired":[140],"voice.We":[141],"publicly":[142],"release":[143],"our":[144,152],"code":[145],"1":[146],"provide":[148],"samples":[150],"experiments":[153],"2":[154],".":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-09T13:55:54.758798","created_date":"2022-10-01T00:00:00"}