{"id":"https://openalex.org/W4408352344","doi":"https://doi.org/10.1109/icassp49660.2025.10889839","title":"RQTalker: Speech-driven 3D Facial Animation via Region-aware Vector Quantization","display_name":"RQTalker: Speech-driven 3D Facial Animation via Region-aware Vector Quantization","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352344","doi":"https://doi.org/10.1109/icassp49660.2025.10889839"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889839","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101941781","display_name":"Yingying Fan","orcid":"https://orcid.org/0000-0002-0010-4198"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingying Fan","raw_affiliation_strings":["Wuhan University,School of Computer Science,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002386773","display_name":"Kaisiyuan Wang","orcid":"https://orcid.org/0000-0002-2120-8383"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaisiyuan Wang","raw_affiliation_strings":["Baidu Inc.,VIS,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc.,VIS,Beijing,China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100707855","display_name":"Hang Zhou","orcid":"https://orcid.org/0000-0002-2616-923X"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Zhou","raw_affiliation_strings":["Baidu Inc.,VIS,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc.,VIS,Beijing,China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090938413","display_name":"Shengyi He","orcid":"https://orcid.org/0000-0001-8521-8639"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengyi He","raw_affiliation_strings":["Baidu Inc.,VIS,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc.,VIS,Beijing,China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100324098","display_name":"Yu Wu","orcid":"https://orcid.org/0000-0002-1680-8253"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wu","raw_affiliation_strings":["Wuhan University,School of Computer Science,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.7003,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.92408425,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9950000047683716,"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":0.9950000047683716,"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/T12290","display_name":"Human Motion and Animation","score":0.9369000196456909,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7499300241470337},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.6628418564796448},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.5122725367546082},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5085362195968628},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4920925498008728},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.47935229539871216},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4602273106575012},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.4211307466030121},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40436917543411255},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.30934637784957886}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7499300241470337},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.6628418564796448},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.5122725367546082},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5085362195968628},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4920925498008728},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.47935229539871216},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4602273106575012},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.4211307466030121},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40436917543411255},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.30934637784957886}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889839","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1485743559","https://openalex.org/W1990883837","https://openalex.org/W2468212864","https://openalex.org/W2563408008","https://openalex.org/W2739192055","https://openalex.org/W2745771616","https://openalex.org/W2752796333","https://openalex.org/W2981263323","https://openalex.org/W3154411171","https://openalex.org/W3175779516","https://openalex.org/W4200630629","https://openalex.org/W4200633626","https://openalex.org/W4382466407","https://openalex.org/W4385536165","https://openalex.org/W4386076250","https://openalex.org/W4387967971","https://openalex.org/W4388157164","https://openalex.org/W4390872742","https://openalex.org/W4390873123","https://openalex.org/W4392903679","https://openalex.org/W4393149781","https://openalex.org/W4399527576","https://openalex.org/W4400527960","https://openalex.org/W4400582137","https://openalex.org/W4400818936","https://openalex.org/W4405779028","https://openalex.org/W4409368359","https://openalex.org/W6849973098","https://openalex.org/W6907631384"],"related_works":["https://openalex.org/W1544039745","https://openalex.org/W2121378366","https://openalex.org/W2999276620","https://openalex.org/W2532377291","https://openalex.org/W1976926596","https://openalex.org/W2989004599","https://openalex.org/W2535923857","https://openalex.org/W3094080214","https://openalex.org/W2156310872","https://openalex.org/W2356609371"],"abstract_inverted_index":{"Speech-driven":[0],"3D":[1,71],"facial":[2,72,108,118,134],"animation":[3,73],"has":[4],"been":[5],"a":[6,43,68,90,94,107,111,142],"long-standing":[7],"topic":[8],"due":[9],"to":[10,27,48,87,106,147],"the":[11,36,39,57,78,102],"complex":[12],"geometry":[13],"and":[14,52,131,155,159],"motion":[15,50,135],"modeling":[16],"as":[17,19,32],"well":[18],"difficulties":[20],"in":[21,56,97],"cross-modality":[22],"learning.":[23],"Current":[24],"studies":[25],"struggle":[26],"synthesize":[28],"human-like":[29],"lip":[30,59],"motions,":[31],"they":[33],"usually":[34],"represent":[35],"movement":[37],"of":[38,101],"entire":[40],"face":[41],"with":[42,63,110],"compressed":[44],"global":[45],"vector,":[46],"leading":[47],"subtle":[49],"loss":[51,128],"thus":[53],"over-smoothed":[54],"movements":[55,119,149],"local":[58,121,133],"region.":[60],"To":[61],"cope":[62],"this":[64],"problem,":[65],"we":[66,139],"propose":[67,141],"new":[69],"speech-driven":[70],"framework":[74],"RQTalker":[75],"based":[76],"on":[77],"Region-aware":[79],"Vector":[80],"Quantization":[81],"mechanism.":[82],"The":[83],"key":[84],"insight":[85],"is":[86],"first":[88],"build":[89],"region-aware":[91,115],"codebook":[92,103,116],"via":[93],"self-reconstruction":[95],"manner,":[96],"which":[98],"each":[99],"part":[100],"physically":[104],"corresponds":[105],"region":[109],"clear":[112],"semantic.":[113],"Our":[114],"divides":[117],"into":[120],"regions":[122],"for":[123],"multiple":[124],"sub-encodings,":[125],"reducing":[126],"information":[127],"from":[129],"compression":[130],"improving":[132],"modeling.":[136],"In":[137],"addition,":[138],"further":[140],"spatial-temporal":[143],"Audio-to-Motion":[144],"Learning":[145],"Module":[146],"produce":[148],"that":[150,163],"are":[151],"spatially":[152],"more":[153],"accurate":[154],"temporally":[156],"consistent.":[157],"Qualitative":[158],"quantitative":[160],"results":[161],"demonstrate":[162],"our":[164],"method":[165],"outperforms":[166],"state-of-the-art":[167],"approaches.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}