{"id":"https://openalex.org/W7133299053","doi":"https://doi.org/10.1109/ijcb65343.2025.11411575","title":"DiffSpeaker: Speech-Driven 3D Facial Animation with Diffusion Transformer","display_name":"DiffSpeaker: Speech-Driven 3D Facial Animation with Diffusion Transformer","publication_year":2025,"publication_date":"2025-09-08","ids":{"openalex":"https://openalex.org/W7133299053","doi":"https://doi.org/10.1109/ijcb65343.2025.11411575"},"language":null,"primary_location":{"id":"doi:10.1109/ijcb65343.2025.11411575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcb65343.2025.11411575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Joint Conference on Biometrics (IJCB)","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/A5127932013","display_name":"Zhiyuan Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhiyuan Ma","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127976308","display_name":"Xiangyu Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Zhu","raw_affiliation_strings":["Chinese Academy of Sciences,MAIS, Institute of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,MAIS, Institute of Automation","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127880599","display_name":"Chen Qian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Qian","raw_affiliation_strings":["SenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shukai Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I1301182553","display_name":"CNH Industrial (Czechia)","ror":"https://ror.org/01ry8n211","country_code":"CZ","type":"company","lineage":["https://openalex.org/I1301182553","https://openalex.org/I4210102001"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Shukai Chen","raw_affiliation_strings":["ZKTeco Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZKTeco Co., Ltd","institution_ids":["https://openalex.org/I1301182553"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127981462","display_name":"Li Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Gao","raw_affiliation_strings":["China Mobile Financial Technology Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Financial Technology Co., Ltd","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035910968","display_name":"Guojun Qi","orcid":"https://orcid.org/0000-0003-4269-2888"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]},{"id":"https://openalex.org/I4210106930","display_name":"Westlake Health Center","ror":"https://ror.org/02cy2d039","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799343972","https://openalex.org/I4210106930"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Guojun Qi","raw_affiliation_strings":["WestLake University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WestLake University","institution_ids":["https://openalex.org/I3133055985","https://openalex.org/I4210106930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127952075","display_name":"Zhaoxiang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoxiang Zhang","raw_affiliation_strings":["Chinese Academy of Sciences,MAIS, Institute of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,MAIS, Institute of Automation","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5127895702","display_name":"Zhen Lei","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Lei","raw_affiliation_strings":["Chinese Academy of Sciences,MAIS, Institute of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,MAIS, Institute of Automation","institution_ids":["https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.66518576,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.8361999988555908,"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":0.8361999988555908,"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":0.0203000009059906,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.01759999990463257,"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/animation","display_name":"Animation","score":0.5608999729156494},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.49149999022483826},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4410000145435333},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.40720000863075256},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.38040000200271606},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.33629998564720154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7021999955177307},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5608999729156494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5047000050544739},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.49149999022483826},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4410000145435333},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43479999899864197},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.40720000863075256},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.38040000200271606},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.33629998564720154},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.29989999532699585},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C194051981","wikidata":"https://www.wikidata.org/wiki/Q1337691","display_name":"Economic shortage","level":3,"score":0.28630000352859497},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.262800008058548}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcb65343.2025.11411575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcb65343.2025.11411575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Joint Conference on Biometrics (IJCB)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337495","display_name":"Technology Development","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1485743559","https://openalex.org/W2154961933","https://openalex.org/W2157331557","https://openalex.org/W2468212864","https://openalex.org/W2737658251","https://openalex.org/W2739192055","https://openalex.org/W2981263323","https://openalex.org/W3096831136","https://openalex.org/W3154411171","https://openalex.org/W3209059054","https://openalex.org/W4200630629","https://openalex.org/W4312933868","https://openalex.org/W4377010269","https://openalex.org/W4385245566","https://openalex.org/W4385681340","https://openalex.org/W4386065764","https://openalex.org/W4386065848","https://openalex.org/W4386076250","https://openalex.org/W4387967971","https://openalex.org/W4388157164","https://openalex.org/W4400818936"],"related_works":[],"abstract_inverted_index":{"Speech-driven":[0],"3D":[1],"facial":[2,123,149],"animation":[3],"is":[4,39,49,155],"important":[5],"for":[6,23,51,86],"many":[7],"multimedia":[8],"applications.":[9],"Recent":[10],"work":[11],"has":[12],"shown":[13],"promise":[14],"in":[15,90,151],"using":[16],"either":[17],"Diffusion":[18,62,127],"models":[19],"or":[20],"Transformer":[21,53],"architectures":[22],"this":[24,38,66],"task.":[25],"However,":[26],"their":[27],"mere":[28],"aggregation":[29],"does":[30],"not":[31],"lead":[32],"to":[33,41,54,102,144,147],"improved":[34],"performance.":[35],"We":[36,112],"suspect":[37],"due":[40],"a":[42,58,71],"shortage":[43],"of":[44],"paired":[45],"audio-4D":[46],"data,":[47],"which":[48],"crucial":[50],"the":[52,61,87,99,106,115,126],"effectively":[55],"perform":[56],"as":[57,84],"denoiser":[59],"within":[60,125],"framework.":[63],"To":[64],"tackle":[65],"issue,":[67],"we":[68],"present":[69],"DiffSpeaker,":[70],"Transformer-based":[72],"network":[73],"equipped":[74],"with":[75],"novel":[76],"biased":[77],"conditional":[78],"attention":[79,100],"modules.":[80],"These":[81],"modules":[82],"serve":[83],"substitutes":[85],"traditional":[88],"self/cross-attention":[89],"standard":[91],"Transformers,":[92],"incorporating":[93],"thoughtfully":[94],"designed":[95],"biases":[96],"that":[97],"steer":[98],"mechanisms":[101],"concentrate":[103],"on":[104,136],"both":[105],"relevant":[107],"task-specific":[108],"and":[109,121,139],"diffusion-related":[110],"conditions.":[111],"also":[113],"explore":[114],"trade-off":[116],"between":[117],"accurate":[118],"lip":[119],"synchronization":[120],"non-verbal":[122],"expressions":[124],"paradigm.":[128],"Experiments":[129],"show":[130],"our":[131],"model":[132],"achieves":[133],"state-of-the-art":[134],"performance":[135],"existing":[137],"benchmarks,":[138],"fast":[140],"inference":[141],"speed":[142],"owing":[143],"its":[145],"ability":[146],"generate":[148],"motions":[150],"parallel.":[152],"Our":[153],"code":[154],"avalable":[156],"at":[157],"https://github.com/theEricMa/DiffSpeaker.":[158]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-04T00:00:00"}
