{"id":"https://openalex.org/W7125901804","doi":"https://doi.org/10.1109/smc58881.2025.11343147","title":"EGSTalker: Real-Time Audio-Driven Talking Head Generation with Efficient Gaussian Deformation","display_name":"EGSTalker: Real-Time Audio-Driven Talking Head Generation with Efficient Gaussian Deformation","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125901804","doi":"https://doi.org/10.1109/smc58881.2025.11343147"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5124071069","display_name":"Tianheng Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianheng Zhu","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Xinjiang Multimodal Intelligent Processing and Information Security Engineering Technology Research Center,Urumqi,China,830017"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Xinjiang Multimodal Intelligent Processing and Information Security Engineering Technology Research Center,Urumqi,China,830017","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062830446","display_name":"Yinfeng Yu","orcid":"https://orcid.org/0000-0003-3089-4140"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinfeng Yu","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Xinjiang Multimodal Intelligent Processing and Information Security Engineering Technology Research Center,Urumqi,China,830017"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Xinjiang Multimodal Intelligent Processing and Information Security Engineering Technology Research Center,Urumqi,China,830017","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124055292","display_name":"Liejun Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liejun Wang","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Xinjiang Multimodal Intelligent Processing and Information Security Engineering Technology Research Center,Urumqi,China,830017"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Xinjiang Multimodal Intelligent Processing and Information Security Engineering Technology Research Center,Urumqi,China,830017","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124119075","display_name":"Fuchun Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuchun Sun","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,Beijing,China,100091"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,Beijing,China,100091","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124134820","display_name":"Wendong Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wendong Zheng","raw_affiliation_strings":["Tianjin University of Technology,School of Electrical Engineering and Automation,Tianjin,China,300382"],"affiliations":[{"raw_affiliation_string":"Tianjin University of Technology,School of Electrical Engineering and Automation,Tianjin,China,300382","institution_ids":["https://openalex.org/I136765683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5124071069"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68465687,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7542","last_page":"7547"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6523000001907349,"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":0.6523000001907349,"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/T11448","display_name":"Face recognition and analysis","score":0.26930001378059387,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.013799999840557575,"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/gaussian","display_name":"Gaussian","score":0.6398000121116638},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.5748999714851379},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5217000246047974},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.426800012588501},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.3610000014305115},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3467000126838684},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.3391000032424927},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.3140999972820282}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7706999778747559},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.6398000121116638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5763000249862671},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5748999714851379},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5529999732971191},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5217000246047974},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.426800012588501},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3610000014305115},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.33809998631477356},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3253999948501587},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C166550679","wikidata":"https://www.wikidata.org/wiki/Q263400","display_name":"Gaussian network model","level":3,"score":0.3077000081539154},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.30390000343322754},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C104317376","wikidata":"https://www.wikidata.org/wiki/Q1894545","display_name":"Gaussian blur","level":5,"score":0.289000004529953},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2874999940395355},{"id":"https://openalex.org/C65892221","wikidata":"https://www.wikidata.org/wiki/Q1113935","display_name":"Gaussian filter","level":3,"score":0.28610000014305115},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C7218915","wikidata":"https://www.wikidata.org/wiki/Q1054475","display_name":"Gaussian function","level":3,"score":0.25589999556541443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2738406145","https://openalex.org/W2949662773","https://openalex.org/W2962785568","https://openalex.org/W3081492798","https://openalex.org/W3197199219","https://openalex.org/W3211147706","https://openalex.org/W4200150166","https://openalex.org/W4200630629","https://openalex.org/W4328050872","https://openalex.org/W4385318467","https://openalex.org/W4385767322","https://openalex.org/W4386066256","https://openalex.org/W4386075787","https://openalex.org/W4390872116","https://openalex.org/W4402727915","https://openalex.org/W4403792004","https://openalex.org/W4403944333","https://openalex.org/W4403998628","https://openalex.org/W4411049949"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"EGSTalker,":[3],"a":[4,54,59,71],"real-time":[5,129],"audio-driven":[6,48],"talking":[7],"head":[8],"generation":[9],"framework":[10,39],"based":[11],"on":[12],"3D":[13,73],"Gaussian":[14,45,74,99],"Splatting":[15],"(3DGS).":[16],"Designed":[17],"to":[18,33,65,88,113],"enhance":[19],"both":[20],"speed":[21],"and":[22,47,58,69,91,109],"visual":[23],"fidelity,":[24],"EGSTalker":[25,105],"requires":[26],"only":[27],"3\u20135":[28],"minutes":[29],"of":[30],"training":[31],"video":[32],"synthesize":[34],"high-quality":[35],"facial":[36],"animations.":[37],"The":[38],"comprises":[40],"two":[41],"key":[42],"stages:":[43],"static":[44],"initialization":[46],"deformation.":[49],"In":[50,76],"the":[51,77,97],"first":[52],"stage,":[53,79],"multi-resolution":[55],"hash":[56],"triplane":[57],"Kolmogorov-Arnold":[60],"Network":[61],"(KAN)":[62],"are":[63],"used":[64],"extract":[66],"spatial":[67,92],"features":[68],"construct":[70],"compact":[72],"representation.":[75],"second":[78],"we":[80],"propose":[81],"an":[82],"Efficient":[83],"Spatial-Audio":[84],"Attention":[85],"(ESAA)":[86],"module":[87],"fuse":[89],"audio":[90],"cues,":[93],"while":[94,116],"KAN":[95],"predicts":[96],"corresponding":[98],"deformations.":[100],"Extensive":[101],"experiments":[102],"demonstrate":[103],"that":[104],"achieves":[106],"rendering":[107],"quality":[108],"lip-sync":[110],"accuracy":[111],"comparable":[112],"state-of-the-art":[114],"methods,":[115],"significantly":[117],"outperforming":[118],"them":[119],"in":[120],"inference":[121],"speed.":[122],"These":[123],"results":[124],"highlight":[125],"EGSTalker\u2019s":[126],"potential":[127],"for":[128],"multimedia":[130],"applications.":[131]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-29T00:00:00"}