{"id":"https://openalex.org/W7043048241","doi":null,"title":"Realistic Speech-Driven Talking Face Synthesis via Audio-Visual Association Exploitation and its Applications","display_name":"Realistic Speech-Driven Talking Face Synthesis via Audio-Visual Association Exploitation and its Applications","publication_year":2024,"publication_date":"2024-11-21","ids":{"openalex":"https://openalex.org/W7043048241"},"language":"en","primary_location":{"id":"pmh:oai:irdb.nii.ac.jp:00897:0006497317","doi":null,"is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100927319","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"doctoral thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100927319","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Sun, Yasheng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Yasheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5082635465","display_name":"Yasheng Sun","orcid":"https://orcid.org/0000-0002-0589-4424","observed_orcids":["https://orcid.org/0000-0002-0589-4424","https://orcid.org/0009-0001-4327-1543"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Yasheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8773999810218811,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8773999810218811,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.08739999681711197,"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/T11448","display_name":"Face recognition and analysis","score":0.014499999582767487,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/audio-visual-association","display_name":"audio-visual association","score":0.9800000190734863},{"id":"https://openalex.org/keywords/speaker-characteristics","display_name":"speaker characteristics","score":0.8529999852180481},{"id":"https://openalex.org/keywords/disentangled-representation-learning","display_name":"disentangled representation learning","score":0.7139999866485596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5688999891281128},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.47760000824928284},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.45739999413490295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4115000069141388},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33649998903274536},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.257999986410141},{"id":"https://openalex.org/C2983325608","wikidata":"https://www.wikidata.org/wiki/Q17084606","display_name":"Data association","level":3,"score":0.24860000610351562},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.24629999697208405},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.24300000071525574},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.24160000681877136},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.24089999496936798},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.23919999599456787},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2337000072002411},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.22789999842643738},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.21819999814033508},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.20909999310970306},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.20059999823570251},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.19460000097751617},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.19269999861717224},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.1923000067472458},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.19220000505447388},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.19030000269412994},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.1881999969482422},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.18729999661445618},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.18719999492168427},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.1850000023841858},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.18299999833106995},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.1826000064611435},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.18219999969005585},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.18140000104904175},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.181099995970726},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.1793999969959259},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.1777999997138977},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.17579999566078186},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.17550000548362732},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.17520000040531158}],"mesh":[],"locations_count":9,"locations":[{"id":"pmh:oai:irdb.nii.ac.jp:00897:0006497317","doi":null,"is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100927319","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"doctoral thesis"},{"id":"pmh:oai:irdb.nii.ac.jp:00894:0007514715","doi":null,"is_oa":true,"landing_page_url":"https://isct.repo.nii.ac.jp/records/2001369","pdf_url":"https://isct.repo.nii.ac.jp/record/2001369/files/1767575164534.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"doctoral thesis"},{"id":"pmh:oai:irdb.nii.ac.jp:00894:0007515031","doi":null,"is_oa":true,"landing_page_url":"https://isct.repo.nii.ac.jp/records/2001685","pdf_url":"https://isct.repo.nii.ac.jp/record/2001685/files/1767575197463.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"doctoral thesis"},{"id":"pmh:oai:irdb.nii.ac.jp:00894:0007527141","doi":null,"is_oa":true,"landing_page_url":"https://isct.repo.nii.ac.jp/records/2002021","pdf_url":"https://isct.repo.nii.ac.jp/record/2002021/files/1767575182046.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"doctoral thesis"},{"id":"pmh:oai:irdb.nii.ac.jp:00897:0006497316","doi":null,"is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100927320","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100927320/ATD100000413/20D38070_yashengsun_summary.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"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":"thesis"},{"id":"pmh:oai:irdb.nii.ac.jp:00897:0007231487","doi":null,"is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100940126","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100940126/ATD100000413/20D38070_SUN_YASHENG_result.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"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":"conference paper"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50720237","doi":null,"is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100927320","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100927320/ATD100000413/","source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"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":"Thesis or Dissertation"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50749384","doi":null,"is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100940126","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100940126/ATD100000413/","source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"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":"Conference Paper"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50720236","doi":null,"is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100927319","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"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":"Thesis or Dissertation"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:00897:0006497317","doi":null,"is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100927319","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"doctoral thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7043048241.pdf","grobid_xml":"https://content.openalex.org/works/W7043048241.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W2603621985","https://openalex.org/W2769666294","https://openalex.org/W2939710050","https://openalex.org/W2964559396","https://openalex.org/W3006439205","https://openalex.org/W3034211329","https://openalex.org/W3087644184","https://openalex.org/W3216586892","https://openalex.org/W4224035735","https://openalex.org/W4281779270","https://openalex.org/W4283026156","https://openalex.org/W4297808394","https://openalex.org/W4298186886","https://openalex.org/W4318718936","https://openalex.org/W4318906029","https://openalex.org/W4319165821","https://openalex.org/W4322718191","https://openalex.org/W4323717348","https://openalex.org/W4366850747","https://openalex.org/W4382469130","https://openalex.org/W4384112212","https://openalex.org/W4385571689","https://openalex.org/W4387294143","https://openalex.org/W4387609319","https://openalex.org/W4388979610","https://openalex.org/W4389217543","https://openalex.org/W4389911993","https://openalex.org/W4393065402","https://openalex.org/W4393178509","https://openalex.org/W4394896914","https://openalex.org/W4396822569","https://openalex.org/W4400818936","https://openalex.org/W4402660084","https://openalex.org/W4409366769","https://openalex.org/W4411472278","https://openalex.org/W4415800534","https://openalex.org/W7133214447","https://openalex.org/W7133218197","https://openalex.org/W7133225605"],"related_works":["https://openalex.org/W7034036849","https://openalex.org/W2621963822","https://openalex.org/W7146008154","https://openalex.org/W6997046654","https://openalex.org/W2405997896","https://openalex.org/W7108726046","https://openalex.org/W7222932653","https://openalex.org/W4408401267","https://openalex.org/W7221015716","https://openalex.org/W7222981859"],"abstract_inverted_index":{"Talking":[0],"face":[1,41,117,133],"synthesis":[2,42],"holds":[3],"significant":[4],"importance":[5],"across":[6],"various":[7],"entertainment":[8],"applications,":[9],"including":[10],"digital":[11],"human":[12,37,80,103,125,148,182],"animation,":[13],"visual":[14,167],"dubbing":[15],"in":[16,39,97],"films,":[17],"and":[18,85,204],"rapid":[19],"production":[20],"of":[21,36,87,115,137,154,181],"short":[22],"videos.To":[23],"promote":[24,173],"realistic":[25],"video":[26],"generation,":[27],"we":[28,161,210],"propose":[29,162],"to":[30,45,58,73,113,163,172,199,216],"fully":[31],"exploit":[32],"the":[33,88,121,152,158,165,193,218],"implicit":[34],"information":[35,101,123,139],"speech":[38,126,142],"talking":[40,67,116,132],"system.In":[43],"contrast":[44],"previous":[46],"works":[47],"that":[48,192],"borrow":[49],"external":[50],"images,":[51],"videos":[52],"or":[53,66,107,144],"labels":[54],"as":[55,141,169],"reference":[56],"source":[57],"explicitly":[59],"provide":[60],"speaker":[61,145],"characteristics":[62,146],"like":[63],"facial":[64],"appearance":[65],"status,":[68],"our":[69,184],"proposed":[70],"framework":[71,185],"attempt":[72],"directly":[74],"infer":[75],"these":[76],"underlying":[77,124],"features":[78],"from":[79,147],"voice,":[81],"thereby":[82],"increasing":[83],"realness":[84],"naturalness":[86],"synthesized":[89],"videos.However,":[90],"this":[91,155],"task":[92],"is":[93,105,127,186,196],"particularly":[94],"challenging":[95],"due":[96],"two":[98],"aspects.1)":[99],"These":[100],"within":[102],"voice":[104],"incomplete":[106],"even":[108],"ambiguous.Such":[109],"uncertainty":[110],"brings":[111],"difficulty":[112],"development":[114],"system":[118],"because":[119],"capturing":[120],"required":[122],"non-trivial.2)":[128],"Successfully":[129],"driving":[130],"a":[131,170,214],"requires":[134],"delicately":[135],"integration":[136],"interleaved":[138],"such":[140],"content":[143],"voice.This":[149],"further":[150],"increases":[151],"complexity":[153],"task.To":[156],"address":[157],"above":[159],"challenge,":[160],"leverage":[164],"explicit":[166],"cues":[168],"bridge":[171],"audio-visual":[174],"association":[175],"learning,":[176],"thus":[177],"facilitating":[178],"extensive":[179],"exploitation":[180],"speech.Specifically,":[183],"divided":[187],"into":[188],"three":[189],"components.To":[190],"ensure":[191],"generation":[194],"progress":[195],"well":[197],"delegated":[198],"each":[200],"specific":[201],"semantic":[202],"space":[203],"prevent":[205],"undesirable":[206],"interference":[207],"among":[208],"them,":[209],"first":[211],"carefully":[212],"derive":[213],"strategy":[215],"disentangle":[217],"*":[219],"Doctoral":[220],"Dissertation,":[221]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-10-10T00:00:00"}
