{"id":"https://openalex.org/W7168793573","doi":"https://doi.org/10.1145/3799902.3811066","title":"EchoAvatar: Real-time Generative Avatar Animation from Audio Streams","display_name":"EchoAvatar: Real-time Generative Avatar Animation from Audio Streams","publication_year":2026,"publication_date":"2026-07-16","ids":{"openalex":"https://openalex.org/W7168793573","doi":"https://doi.org/10.1145/3799902.3811066"},"language":null,"primary_location":{"id":"doi:10.1145/3799902.3811066","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811066","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 Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3799902.3811066","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047779067","display_name":"Bohong Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bohong Chen","raw_affiliation_strings":["State Key Lab of CAD&amp;CG, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-1036-7737","affiliations":[{"raw_affiliation_string":"State Key Lab of CAD&amp;CG, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063811746","display_name":"Yumeng Li","orcid":"https://orcid.org/0009-0007-6558-4165"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yumeng Li","raw_affiliation_strings":["State Key Lab of CAD&amp;CG, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-6558-4165","affiliations":[{"raw_affiliation_string":"State Key Lab of CAD&amp;CG, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140980183","display_name":"Yinglin Xu","orcid":"https://orcid.org/0009-0008-9804-3872"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinglin Xu","raw_affiliation_strings":["State Key Lab of CAD&amp;CG, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-9804-3872","affiliations":[{"raw_affiliation_string":"State Key Lab of CAD&amp;CG, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008766810","display_name":"Youyi Zheng","orcid":"https://orcid.org/0000-0002-9120-9592"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youyi Zheng","raw_affiliation_strings":["State Key Lab of CAD&amp;CG, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9120-9592","affiliations":[{"raw_affiliation_string":"State Key Lab of CAD&amp;CG, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004008347","display_name":"Yanlin Weng","orcid":"https://orcid.org/0000-0001-5223-4253"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanlin Weng","raw_affiliation_strings":["State Key Lab of CAD&amp;CG, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-7043-4410","affiliations":[{"raw_affiliation_string":"State Key Lab of CAD&amp;CG, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027671723","display_name":"Kun Zhou","orcid":"https://orcid.org/0000-0003-4243-6112"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Zhou","raw_affiliation_strings":["State Key Lab of CAD&amp;CG, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4243-6112","affiliations":[{"raw_affiliation_string":"State Key Lab of CAD&amp;CG, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5885999798774719},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.49630001187324524},{"id":"https://openalex.org/keywords/avatar","display_name":"Avatar","score":0.4749999940395355},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.47360000014305115},{"id":"https://openalex.org/keywords/character-animation","display_name":"Character animation","score":0.43209999799728394},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.42989999055862427},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.4106000065803528},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4081000089645386},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.3813000023365021}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8518999814987183},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5885999798774719},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.49630001187324524},{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.4749999940395355},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.47360000014305115},{"id":"https://openalex.org/C90697248","wikidata":"https://www.wikidata.org/wiki/Q1062896","display_name":"Character animation","level":4,"score":0.43209999799728394},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.42989999055862427},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.4106000065803528},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4081000089645386},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.3813000023365021},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37220001220703125},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3718999922275543},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34139999747276306},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.3379000127315521},{"id":"https://openalex.org/C144430266","wikidata":"https://www.wikidata.org/wiki/Q839721","display_name":"Interactivity","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C38956757","wikidata":"https://www.wikidata.org/wiki/Q716215","display_name":"Audio feedback","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.2978000044822693},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.28189998865127563},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C191172861","wikidata":"https://www.wikidata.org/wiki/Q7899321","display_name":"Upstream (networking)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.25220000743865967},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3799902.3811066","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811066","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 Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3799902.3811066","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811066","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 Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3405827317","display_name":null,"funder_award_id":"62421003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":73,"referenced_works":["https://openalex.org/W815877816","https://openalex.org/W2008208299","https://openalex.org/W2135431835","https://openalex.org/W2141855524","https://openalex.org/W2235920218","https://openalex.org/W2811167645","https://openalex.org/W2949924544","https://openalex.org/W2962795401","https://openalex.org/W3002310794","https://openalex.org/W3009042479","https://openalex.org/W3024902055","https://openalex.org/W3048550213","https://openalex.org/W3083173864","https://openalex.org/W3198131199","https://openalex.org/W3215615641","https://openalex.org/W4214717370","https://openalex.org/W4230429791","https://openalex.org/W4230563027","https://openalex.org/W4231807801","https://openalex.org/W4285981714","https://openalex.org/W4303448003","https://openalex.org/W4304080460","https://openalex.org/W4308222716","https://openalex.org/W4312309978","https://openalex.org/W4312437946","https://openalex.org/W4312674262","https://openalex.org/W4312765683","https://openalex.org/W4321351659","https://openalex.org/W4377010269","https://openalex.org/W4385283834","https://openalex.org/W4385764101","https://openalex.org/W4386075984","https://openalex.org/W4386755513","https://openalex.org/W4387963302","https://openalex.org/W4389665966","https://openalex.org/W4390541209","https://openalex.org/W4393158904","https://openalex.org/W4400819107","https://openalex.org/W4400822426","https://openalex.org/W4400839976","https://openalex.org/W4402703119","https://openalex.org/W4402727590","https://openalex.org/W4402754111","https://openalex.org/W4403792047","https://openalex.org/W4404966690","https://openalex.org/W4412588567","https://openalex.org/W4412590231","https://openalex.org/W4412595661","https://openalex.org/W4412596354","https://openalex.org/W4413146746","https://openalex.org/W4413147016","https://openalex.org/W4413147786","https://openalex.org/W4413155966","https://openalex.org/W4413156691","https://openalex.org/W4413259119","https://openalex.org/W4414747307","https://openalex.org/W4415743520","https://openalex.org/W4417124905","https://openalex.org/W4417125294","https://openalex.org/W4417125341","https://openalex.org/W4417125375","https://openalex.org/W7131116209","https://openalex.org/W7133208539","https://openalex.org/W7133211372","https://openalex.org/W7133229781","https://openalex.org/W7133240289","https://openalex.org/W7133240349","https://openalex.org/W7160012713","https://openalex.org/W7160037713","https://openalex.org/W7160040527","https://openalex.org/W7160074091","https://openalex.org/W7160104245","https://openalex.org/W7160157512"],"related_works":[],"abstract_inverted_index":{"Real-time":[0],"synthesis":[1],"of":[2,29,79,127],"high-fidelity":[3],"3D":[4],"character":[5],"motion":[6,60,82,187],"from":[7,61,83],"audio":[8,31,85,96],"is":[9,73],"a":[10,51,74,89,139,165],"pivotal":[11],"component":[12],"for":[13,168,196],"next-generation":[14],"interactive":[15,173],"avatars":[16],"and":[17,43,64,107,189,203],"virtual":[18],"assistants.":[19],"However,":[20],"most":[21],"existing":[22],"approaches":[23],"are":[24,34,205],"limited":[25],"to":[26,36,55,70,101,123,148],"offline":[27],"processing":[28],"complete":[30],"sequences":[32],"or":[33,115],"constrained":[35],"specific":[37],"domains,":[38],"rarely":[39],"handling":[40],"both":[41],"speech":[42,63,106],"music":[44,65,109],"effectively.":[45],"In":[46],"this":[47,155],"paper,":[48],"we":[49,119,131],"introduce":[50],"novel":[52],"framework":[53,162],"designed":[54],"generate":[56],"continuous,":[57],"coherent":[58],"full-body":[59],"streaming":[62,76],"with":[66,135,157],"low":[67],"latency.":[68],"Central":[69],"our":[71,161,180],"approach":[72],"unified":[75],"architecture":[77],"capable":[78],"synthesizing":[80],"continuous":[81],"incremental":[84],"inputs.":[86],"We":[87],"employ":[88],"robust":[90],"training":[91],"strategy":[92],"that":[93,142,179],"enforces":[94],"strong":[95],"dependency,":[97],"allowing":[98],"the":[99,125,193],"model":[100],"seamlessly":[102],"generalize":[103],"across":[104],"conversational":[105],"rhythmic":[108],"without":[110],"requiring":[111],"explicit":[112,150],"domain":[113],"labels":[114],"mode":[116],"switching.":[117],"Additionally,":[118],"explored":[120],"Reinforcement":[121],"Learning":[122],"refine":[124],"quality":[126,188],"online":[128],"generation.":[129],"Furthermore,":[130],"bridge":[132],"reactive":[133],"animation":[134],"intent-driven":[136],"behavior":[137],"via":[138],"tool-call":[140],"interface":[141],"allows":[143],"upstream":[144],"Large":[145],"Language":[146],"Models":[147],"inject":[149],"semantic":[151],"control.":[152],"By":[153],"combining":[154],"controllability":[156],"stream":[158],"audio-driven":[159],"synthesis,":[160],"serves":[163],"as":[164],"plug-and-play":[166],"solution":[167],"transforming":[169],"voice":[170],"agents":[171],"into":[172],"humanoid":[174],"avatars.":[175],"Extensive":[176],"experiments":[177],"demonstrate":[178],"method":[181],"outperforms":[182],"state-of-the-art":[183],"real-time":[184],"baselines":[185],"in":[186],"synchronization":[190],"while":[191],"maintaining":[192],"flexibility":[194],"required":[195],"live":[197],"deployment.":[198],"Our":[199],"code,":[200],"pre-trained":[201],"models,":[202],"videos":[204],"available":[206],"at":[207],"https://robinwitch.github.io/EchoAvatar-Page.":[208]},"counts_by_year":[],"updated_date":"2026-07-17T05:58:32.477365","created_date":"2026-07-17T00:00:00"}
