{"id":"https://openalex.org/W7128925556","doi":"https://doi.org/10.1145/3788731.3788741","title":"TalkPersonaDiff: High-Fidelity Speech-Driven 3D Facial Animation Generation via Unified Multimodal Synergistic Encoding and Dual-Style Modulation","display_name":"TalkPersonaDiff: High-Fidelity Speech-Driven 3D Facial Animation Generation via Unified Multimodal Synergistic Encoding and Dual-Style Modulation","publication_year":2025,"publication_date":"2025-12-19","ids":{"openalex":"https://openalex.org/W7128925556","doi":"https://doi.org/10.1145/3788731.3788741"},"language":null,"primary_location":{"id":"doi:10.1145/3788731.3788741","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788731.3788741","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Embodied Intelligence and Large Models","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3788731.3788741","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086894201","display_name":"Peng Ouyang","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Peng Ouyang","raw_affiliation_strings":["School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126027813","display_name":"Zhuoyuan Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuoyuan Yu","raw_affiliation_strings":["School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126024900","display_name":"Tong Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Wu","raw_affiliation_strings":["School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125999406","display_name":"Zhiqian Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqian Zhang","raw_affiliation_strings":["School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5086894201"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.75145869,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"65","last_page":"70"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.6380000114440918,"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/T11448","display_name":"Face recognition and analysis","score":0.6380000114440918,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.29249998927116394,"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":0.033799998462200165,"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/animation","display_name":"Animation","score":0.6168000102043152},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5327000021934509},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5177000164985657},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.5098999738693237},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4997999966144562},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4690000116825104},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4180000126361847},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.397599995136261}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7638999819755554},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.6168000102043152},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5327000021934509},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5177000164985657},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.5098999738693237},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4997999966144562},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4690000116825104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46369999647140503},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4180000126361847},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.397599995136261},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35260000824928284},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.30570000410079956},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C79880414","wikidata":"https://www.wikidata.org/wiki/Q5275338","display_name":"Differential coding","level":3,"score":0.2989000082015991},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2736000120639801},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.2572999894618988},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3788731.3788741","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788731.3788741","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Embodied Intelligence and Large Models","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3788731.3788741","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788731.3788741","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Embodied Intelligence and Large Models","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1554803342","https://openalex.org/W2154961933","https://openalex.org/W2468212864","https://openalex.org/W2737658251","https://openalex.org/W2739192055","https://openalex.org/W2769666294","https://openalex.org/W2981263323","https://openalex.org/W3209984917","https://openalex.org/W4200630629","https://openalex.org/W4243250497","https://openalex.org/W4386076250","https://openalex.org/W4390872742","https://openalex.org/W4390873123","https://openalex.org/W4399527576","https://openalex.org/W4400818936"],"related_works":[],"abstract_inverted_index":{"Speech-driven":[0],"3D":[1,94],"facial":[2],"animation":[3,95],"is":[4],"critical":[5],"for":[6],"virtual":[7],"humans,":[8],"yet":[9],"balancing":[10],"Long-term":[11],"Identity":[12],"Consistency":[13],"and":[14,39,61,75,88],"Fine-grained":[15],"Lip-sync":[16],"in":[17,42,83],"long":[18],"sequences":[19],"remains":[20],"challenging.":[21],"We":[22],"propose":[23],"TalkPersonaDiff,":[24],"a":[25,30,43,53],"conditional":[26,66],"diffusion":[27],"framework":[28],"featuring":[29],"Unified":[31],"Multimodal":[32],"Synergistic":[33],"Encoder":[34],"to":[35,47,64],"align":[36],"speech":[37],"semantics":[38],"identity":[40,84],"priors":[41],"latent":[44],"space.":[45],"Furthermore,":[46],"mitigate":[48],"condition":[49],"forgetting,":[50],"we":[51],"design":[52],"Dual-Style":[54],"Modulation":[55],"Mechanism":[56],"that":[57,78],"employs":[58],"global":[59],"injection":[60],"local":[62],"re-weighting":[63],"maintain":[65],"efficacy":[67],"throughout":[68],"the":[69],"denoising":[70],"process.":[71],"Experiments":[72],"on":[73],"BIWI":[74],"VOCASET":[76],"demonstrate":[77],"TalkPersonaDiff":[79],"outperforms":[80],"mainstream":[81],"methods":[82],"distinctiveness,":[85],"lip-sync":[86],"accuracy,":[87],"temporal":[89],"smoothness,":[90],"achieving":[91],"high-fidelity,":[92],"personalized":[93],".":[96]},"counts_by_year":[],"updated_date":"2026-02-23T20:09:44.859080","created_date":"2026-02-15T00:00:00"}