{"id":"https://openalex.org/W3135418837","doi":"https://doi.org/10.23919/eusipco54536.2021.9616249","title":"Improving transfer of expressivity for end-to-end multispeaker text-to-speech synthesis","display_name":"Improving transfer of expressivity for end-to-end multispeaker text-to-speech synthesis","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3135418837","doi":"https://doi.org/10.23919/eusipco54536.2021.9616249","mag":"3135418837"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616249","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616249","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.archives-ouvertes.fr/hal-02978485","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026752360","display_name":"Ajinkya Kulkarni","orcid":"https://orcid.org/0000-0003-1423-3676"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Ajinkya Kulkarni","raw_affiliation_strings":["Université de Lorraine, CNRS, Inria, LORIA,Nancy,France,F-54000","Speech Modeling for Facilitating Oral-Based Communication"],"affiliations":[{"raw_affiliation_string":"Université de Lorraine, CNRS, Inria, LORIA,Nancy,France,F-54000","institution_ids":["https://openalex.org/I4210121838","https://openalex.org/I1294671590","https://openalex.org/I90183372"]},{"raw_affiliation_string":"Speech Modeling for Facilitating Oral-Based Communication","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039712983","display_name":"Vincent Colotte","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Vincent Colotte","raw_affiliation_strings":["Université de Lorraine, CNRS, Inria, LORIA,Nancy,France,F-54000","Speech Modeling for Facilitating Oral-Based Communication"],"affiliations":[{"raw_affiliation_string":"Université de Lorraine, CNRS, Inria, LORIA,Nancy,France,F-54000","institution_ids":["https://openalex.org/I4210121838","https://openalex.org/I1294671590","https://openalex.org/I90183372"]},{"raw_affiliation_string":"Speech Modeling for Facilitating Oral-Based Communication","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030903462","display_name":"Denis Jouvet","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Denis Jouvet","raw_affiliation_strings":["Université de Lorraine, CNRS, Inria, LORIA,Nancy,France,F-54000","Speech Modeling for Facilitating Oral-Based Communication"],"affiliations":[{"raw_affiliation_string":"Université de Lorraine, CNRS, Inria, LORIA,Nancy,France,F-54000","institution_ids":["https://openalex.org/I4210121838","https://openalex.org/I1294671590","https://openalex.org/I90183372"]},{"raw_affiliation_string":"Speech Modeling for Facilitating Oral-Based Communication","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5026752360"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210121838","https://openalex.org/I90183372"],"apc_list":null,"apc_paid":null,"fwci":1.1417,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.80994639,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"31","last_page":"35"},"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/T11309","display_name":"Music and Audio Processing","score":0.996999979019165,"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/T10028","display_name":"Topic Modeling","score":0.9957000017166138,"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/computer-science","display_name":"Computer science","score":0.7798819541931152},{"id":"https://openalex.org/keywords/expressivity","display_name":"Expressivity","score":0.7244425415992737},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6420038342475891},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6160783767700195},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6039206385612488},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.500835657119751},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4988272190093994},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4933847486972809},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39973339438438416},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.32068687677383423}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7798819541931152},{"id":"https://openalex.org/C92811239","wikidata":"https://www.wikidata.org/wiki/Q20998670","display_name":"Expressivity","level":2,"score":0.7244425415992737},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6420038342475891},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6160783767700195},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6039206385612488},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.500835657119751},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4988272190093994},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4933847486972809},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39973339438438416},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32068687677383423},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616249","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616249","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-02978485v2","is_oa":true,"landing_page_url":"https://hal.archives-ouvertes.fr/hal-02978485","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EUSIPCO 2021","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:HAL:hal-02978485v3","is_oa":true,"landing_page_url":"https://hal.science/hal-02978485","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://eusipco2021.org/","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-02978485v2","is_oa":true,"landing_page_url":"https://hal.archives-ouvertes.fr/hal-02978485","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EUSIPCO 2021","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7099999785423279}],"awards":[],"funders":[{"id":"https://openalex.org/F4320313934","display_name":"Institut national de recherche en informatique et en automatique (INRIA)","ror":"https://ror.org/02kvxyf05"},{"id":"https://openalex.org/F4320322892","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73"},{"id":"https://openalex.org/F4320333359","display_name":"College of Natural Resources and Sciences, Humboldt State University","ror":null},{"id":"https://openalex.org/F4320333435","display_name":"Virginia Agricultural Experiment Station, Virginia Polytechnic Institute and State University","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1975163393","https://openalex.org/W2555897561","https://openalex.org/W2604184139","https://openalex.org/W2607084763","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2805064398","https://openalex.org/W2895608766","https://openalex.org/W2904459034","https://openalex.org/W2962691331","https://openalex.org/W2963223306","https://openalex.org/W2963300588","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W2969656782","https://openalex.org/W2972699445","https://openalex.org/W3015796413","https://openalex.org/W3023996010","https://openalex.org/W3024078678","https://openalex.org/W4288107051","https://openalex.org/W4289383906","https://openalex.org/W4295731579","https://openalex.org/W6644048793","https://openalex.org/W6730323794","https://openalex.org/W6736356763","https://openalex.org/W6750489868","https://openalex.org/W6751878434","https://openalex.org/W6755300632","https://openalex.org/W6760752336","https://openalex.org/W6765039917"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2048138016","https://openalex.org/W3013693939","https://openalex.org/W2088854863","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W1976719989"],"abstract_inverted_index":{"The":[0,23,146],"main":[1],"goal":[2],"of":[3,62,88,103,135],"this":[4],"work":[5],"is":[6,21],"to":[7,46,64,81,97],"generate":[8],"expressive":[9,18,41,55],"speech":[10,19,29],"in":[11,51,116,159,165],"different":[12,110],"speaker's":[13,67,168],"voices":[14],"for":[15,58,114,143],"which":[16],"no":[17],"data":[20],"available.":[22],"presented":[24],"approach":[25],"conditions":[26],"Tacotron":[27],"2":[28],"synthesis":[30],"with":[31,77,108],"latent":[32,100,136],"representations":[33],"extracted":[34,138],"from":[35,139],"text,":[36],"speaker":[37],"identity,":[38],"and":[39,124],"reference":[40],"Mel":[42],"spectrogram.":[43],"We":[44,69,105,128],"propose":[45],"use":[47],"multiclass":[48,78,152],"N-pair":[49,79,153],"loss":[50,80,90,154],"the":[52,60,65,73,89,95,99,117,130,133,140,160,166],"end-to-end":[53,74],"multispeaker":[54],"Text-To-Speech":[56],"(TTS)":[57],"improving":[59],"transfer":[61],"expressivity":[63,115,131,141,164],"target":[66],"voice.":[68,169],"have":[70,106],"jointly":[71],"trained":[72],"(E2E)":[75],"TTS":[76],"discriminate":[82],"between":[83],"various":[84],"emotions.":[85,104],"This":[86],"augmentation":[87],"function":[91],"during":[92],"training":[93,161],"paves":[94],"way":[96],"enhance":[98],"space":[101],"representation":[102,137],"experimented":[107],"two":[109],"neural":[111],"network":[112],"architectures":[113],"encoder,":[118],"namely":[119],"global":[120],"style":[121],"token":[122],"(GST)":[123],"variational":[125],"autoencoder":[126],"(VAE).":[127],"transferred":[129],"using":[132],"mean":[134],"encoder":[142],"each":[144],"emotion.":[145],"obtained":[147],"results":[148],"show":[149],"that":[150],"adding":[151],"based":[155],"deep":[156],"metric":[157],"learning":[158],"process":[162],"improves":[163],"desired":[167]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}