{"id":"https://openalex.org/W4380264398","doi":"https://doi.org/10.3389/frai.2023.1142997","title":"Zero-shot style transfer for gesture animation driven by text and speech using adversarial disentanglement of multimodal style encoding","display_name":"Zero-shot style transfer for gesture animation driven by text and speech using adversarial disentanglement of multimodal style encoding","publication_year":2023,"publication_date":"2023-06-12","ids":{"openalex":"https://openalex.org/W4380264398","doi":"https://doi.org/10.3389/frai.2023.1142997","pmid":"https://pubmed.ncbi.nlm.nih.gov/37377638"},"language":"en","primary_location":{"id":"doi:10.3389/frai.2023.1142997","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2023.1142997","pdf_url":"https://www.frontiersin.org/articles/10.3389/frai.2023.1142997/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/articles/10.3389/frai.2023.1142997/pdf?isPublishedV2=False","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068708404","display_name":"Mireille Fares","orcid":"https://orcid.org/0009-0009-0947-7490"},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210150358","display_name":"Institut Syst\u00e8mes Intelligents et de Robotique","ror":"https://ror.org/05neq8668","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210150358","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I4389425508","display_name":"Sciences et Technologies de la Musique et du Son","ror":"https://ror.org/025xvn046","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2802818602","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4210102700","https://openalex.org/I4389425508"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Mireille Fares","raw_affiliation_strings":["The Institute of Intelligent Systems and Robotics (ISIR), Sciences et Technologies de la Musique et du Son (STMS), Sorbonne University, Paris, France","Institut des Syst\u00e8mes Intelligents et de Robotique","Sciences et Technologies de la Musique et du Son"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Institute of Intelligent Systems and Robotics (ISIR), Sciences et Technologies de la Musique et du Son (STMS), Sorbonne University, Paris, France","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I4210150358","https://openalex.org/I4389425508"]},{"raw_affiliation_string":"Institut des Syst\u00e8mes Intelligents et de Robotique","institution_ids":["https://openalex.org/I4210150358"]},{"raw_affiliation_string":"Sciences et Technologies de la Musique et du Son","institution_ids":["https://openalex.org/I4389425508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079026902","display_name":"Catherine P\u00e9lachaud","orcid":"https://orcid.org/0000-0003-1008-0799"},"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/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210150358","display_name":"Institut Syst\u00e8mes Intelligents et de Robotique","ror":"https://ror.org/05neq8668","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210150358","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Catherine Pelachaud","raw_affiliation_strings":["Centre National de la Recherche Scientifique (CNRS), The Institute of Intelligent Systems and Robotics (ISIR), Sorbonne University, Paris, France","Perception, Interaction, Robotique sociales"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre National de la Recherche Scientifique (CNRS), The Institute of Intelligent Systems and Robotics (ISIR), Sorbonne University, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210150358"]},{"raw_affiliation_string":"Perception, Interaction, Robotique sociales","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042745853","display_name":"Nicolas Obin","orcid":"https://orcid.org/0000-0002-5236-5306"},"institutions":[{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4389425508","display_name":"Sciences et Technologies de la Musique et du Son","ror":"https://ror.org/025xvn046","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2802818602","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4210102700","https://openalex.org/I4389425508"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Obin","raw_affiliation_strings":["Sciences et Technologies de la Musique et du Son (STMS), Sorbonne University, Paris, France","Analyse et synth\u00e8se sonores [Paris]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sciences et Technologies de la Musique et du Son (STMS), Sorbonne University, Paris, France","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4389425508"]},{"raw_affiliation_string":"Analyse et synth\u00e8se sonores [Paris]","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5068708404"],"corresponding_institution_ids":["https://openalex.org/I39804081","https://openalex.org/I4210150358","https://openalex.org/I4389425508"],"apc_list":{"value":2125,"currency":"USD","value_usd":2125},"apc_paid":{"value":1882,"currency":"EUR","value_usd":2029},"fwci":2.0673,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.86387308,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"6","issue":null,"first_page":"1142997","last_page":"1142997"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9959999918937683,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9944000244140625,"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/gesture","display_name":"Gesture","score":0.7436575293540955},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7129566073417664},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5212786197662354},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5120614171028137},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.49076637625694275},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4885905683040619},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.4648835361003876},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4200108051300049},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40319618582725525}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.7436575293540955},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7129566073417664},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5212786197662354},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5120614171028137},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.49076637625694275},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4885905683040619},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.4648835361003876},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4200108051300049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40319618582725525},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"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":6,"locations":[{"id":"doi:10.3389/frai.2023.1142997","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2023.1142997","pdf_url":"https://www.frontiersin.org/articles/10.3389/frai.2023.1142997/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},{"id":"pmid:37377638","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37377638","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in artificial intelligence","raw_type":null},{"id":"pmh:oai:HAL:hal-03972415v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03972415","pdf_url":"https://hal.science/hal-03972415/document","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":"2023","raw_type":"info:eu-repo/semantics/preprint"},{"id":"pmh:oai:HAL:hal-04293262v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04293262","pdf_url":"https://hal.science/hal-04293262/document","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":"Frontiers in Artificial Intelligence, 2023, 6, pp.:114299. &#x27E8;10.3389/frai.2023.1142997&#x27E9;","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pubmedcentral.nih.gov:10291316","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10291316","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10291316/pdf/frai-06-1142997.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Artif Intell","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:cf943fba79f04feda7194837bdfd6d7e","is_oa":true,"landing_page_url":"https://doaj.org/article/cf943fba79f04feda7194837bdfd6d7e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Artificial Intelligence, Vol 6 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/frai.2023.1142997","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2023.1142997","pdf_url":"https://www.frontiersin.org/articles/10.3389/frai.2023.1142997/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6299999952316284}],"awards":[{"id":"https://openalex.org/G1189697078","display_name":null,"funder_award_id":"ANR\u201311\u2013LABX\u201365","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G2647246237","display_name":null,"funder_award_id":"ANR-11IDEX-0004-02","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G4866930200","display_name":null,"funder_award_id":"ANR-11-IDEX","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G5615659713","display_name":null,"funder_award_id":"IDEX-0004-02","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G6654833908","display_name":"Sorbonne Universit\u00e9s \u00e0 Paris pour l'Enseignement et la Recherche","funder_award_id":"ANR-11-IDEX-0004","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4380264398.pdf"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W63438600","https://openalex.org/W1534876773","https://openalex.org/W1969681536","https://openalex.org/W1974473538","https://openalex.org/W2007337857","https://openalex.org/W2024785871","https://openalex.org/W2035046981","https://openalex.org/W2053759160","https://openalex.org/W2072617587","https://openalex.org/W2124003719","https://openalex.org/W2131123711","https://openalex.org/W2131734538","https://openalex.org/W2151539117","https://openalex.org/W2475708382","https://openalex.org/W2621350877","https://openalex.org/W2739192055","https://openalex.org/W2780124704","https://openalex.org/W2802076562","https://openalex.org/W2807935342","https://openalex.org/W2808706139","https://openalex.org/W2901872500","https://openalex.org/W2922298118","https://openalex.org/W2962795401","https://openalex.org/W2981133004","https://openalex.org/W2981263323","https://openalex.org/W2981802563","https://openalex.org/W3002310794","https://openalex.org/W3036120140","https://openalex.org/W3094077204","https://openalex.org/W3099073275","https://openalex.org/W3102619627","https://openalex.org/W3105015787","https://openalex.org/W3196974791","https://openalex.org/W3202848120","https://openalex.org/W4214883111","https://openalex.org/W4230840449","https://openalex.org/W4239029363","https://openalex.org/W4241614188","https://openalex.org/W4245188294","https://openalex.org/W4286904667","https://openalex.org/W4312462635","https://openalex.org/W4385245566","https://openalex.org/W6679821868","https://openalex.org/W6739139180","https://openalex.org/W6752888775","https://openalex.org/W6774263716","https://openalex.org/W6781084731","https://openalex.org/W6805404194","https://openalex.org/W6891824578"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2942893872","https://openalex.org/W2016904525"],"abstract_inverted_index":{"Modeling":[0],"virtual":[1],"agents":[2],"with":[3,314],"behavior":[4,162],"style":[5,33,47,64,92,99,163,176,197,208,246,274,280],"is":[6,79,127,151,172,253],"one":[7],"factor":[8],"for":[9],"personalizing":[10],"human-agent":[11],"interaction.":[12],"We":[13,62,248,301],"propose":[14],"an":[15],"efficient":[16],"yet":[17],"effective":[18],"machine":[19],"learning":[20],"approach":[21,310],"to":[22,95,128,152,173,202,255,282,307],"synthesize":[23,256],"gestures":[24,131,158,227,257],"driven":[25,49],"by":[26,50,81,277],"prosodic":[27],"features":[28],"and":[29,84,91,145,217,219,236,241,267,304,311],"text":[30,146],"in":[31,287],"the":[32,54,72,98,111,130,138,154,160,185,230,233,244,263,269,278,283,293],"of":[34,59,89,102,110,124,132,140,165,178,190,232,258,271],"different":[35],"speakers":[36,179],"including":[37],"those":[38],"unseen":[39,180],"during":[40,181],"training.":[41],"Our":[42,187],"model":[43,126,252,294],"performs":[44],"zero-shot":[45,175,289],"multimodal":[46,51,82,161,213],"transfer":[48,177,268],"data":[52,106,214],"from":[53,209],"PATS":[55],"database":[56],"containing":[57],"videos":[58],"various":[60],"speakers.":[61],"view":[63],"as":[65],"being":[66],"pervasive;":[67],"while":[68,76],"speaking,":[69],"it":[70,313],"colors":[71],"communicative":[73],"behaviors":[74],"expressivity":[75],"speech":[77],"content":[78,90,139,231],"carried":[80],"signals":[83],"text.":[85],"This":[86],"disentanglement":[87],"scheme":[88],"allows":[93],"us":[94],"directly":[96],"infer":[97],"embedding":[100,164,207],"even":[101],"a":[103,133,166,195,204,210,221,238,259,288,297],"speaker":[104,135,196,206,212,240,245,261,273,279,299],"whose":[105],"are":[107],"not":[108],"part":[109],"training":[112,118,182],"phase,":[113],"without":[114,183],"requiring":[115],"any":[116],"further":[117],"or":[119],"fine-tuning.":[120],"The":[121,148,169],"first":[122],"goal":[123,150,171],"our":[125,251,309],"generate":[129,203],"source":[134,155,239,260],"based":[136,228],"on":[137,159,229,243],"two":[141,191,264],"input":[142,234,265],"modalities\u2013Mel":[143],"spectrogram":[144],"semantics.":[147],"second":[149],"condition":[153],"speaker's":[156],"predicted":[157],"target":[167,211,272],"speaker.":[168],"third":[170],"allow":[174],"re-training":[184],"model.":[186],"system":[188],"consists":[189],"main":[192],"components:":[193],"(1)":[194],"encoder":[198,281],"network":[199,224],"that":[200,225,250,292],"learns":[201],"fixed-dimensional":[205],"(mel-spectrogram,":[215],"pose,":[216],"text)":[218],"(2)":[220],"sequence-to-sequence":[222],"synthesis":[223],"synthesizes":[226],"modalities\u2014text":[235],"mel-spectrogram\u2014of":[237],"conditioned":[242],"embedding.":[247],"evaluate":[249],"able":[254],"given":[262],"modalities":[266],"knowledge":[270],"variability":[275],"learned":[276,296],"gesture":[284],"generation":[285],"task":[286],"setup,":[290],"indicating":[291],"has":[295],"high-quality":[298],"representation.":[300],"conduct":[302],"objective":[303],"subjective":[305],"evaluations":[306],"validate":[308],"compare":[312],"baselines.":[315]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}
