{"id":"https://openalex.org/W7116709165","doi":"https://doi.org/10.1109/thms.2025.3640719","title":"Speech2Blend: A Hybrid Network for Speech-Driven 3-D Facial Animation by Learning Blendshape","display_name":"Speech2Blend: A Hybrid Network for Speech-Driven 3-D Facial Animation by Learning Blendshape","publication_year":2025,"publication_date":"2025-12-22","ids":{"openalex":"https://openalex.org/W7116709165","doi":"https://doi.org/10.1109/thms.2025.3640719"},"language":null,"primary_location":{"id":"doi:10.1109/thms.2025.3640719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/thms.2025.3640719","pdf_url":null,"source":{"id":"https://openalex.org/S2476799526","display_name":"IEEE Transactions on Human-Machine Systems","issn_l":"2168-2291","issn":["2168-2291","2168-2305"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Human-Machine Systems","raw_type":"journal-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/A5121021236","display_name":"Lei Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lei Wang","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049019844","display_name":"Gongbin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gongbin Chen","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120972912","display_name":"Feng Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Liu","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121009323","display_name":"Jiaji Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaji Wu","raw_affiliation_strings":["School of Electronic Engineering, Xidian University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101705358","display_name":"Jun Cheng","orcid":"https://orcid.org/0000-0002-3131-3275"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Cheng","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5121021236"],"corresponding_institution_ids":["https://openalex.org/I4210145761"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.63138075,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"56","issue":"1","first_page":"48","last_page":"57"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9380000233650208,"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":0.9380000233650208,"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":0.01940000057220459,"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":0.01600000075995922,"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":0.7064999938011169},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.699999988079071},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5151000022888184},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.5056999921798706},{"id":"https://openalex.org/keywords/skeletal-animation","display_name":"Skeletal animation","score":0.41350001096725464},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3968999981880188},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.38440001010894775},{"id":"https://openalex.org/keywords/compatibility","display_name":"Compatibility (geochemistry)","score":0.3840999901294708}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8246999979019165},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.7064999938011169},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.699999988079071},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5151000022888184},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.5056999921798706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4864000082015991},{"id":"https://openalex.org/C44710944","wikidata":"https://www.wikidata.org/wiki/Q1813564","display_name":"Skeletal animation","level":5,"score":0.41350001096725464},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3968999981880188},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C2778648169","wikidata":"https://www.wikidata.org/wiki/Q967768","display_name":"Compatibility (geochemistry)","level":2,"score":0.3840999901294708},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.37299999594688416},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C60851780","wikidata":"https://www.wikidata.org/wiki/Q17056736","display_name":"Interactive skeleton-driven simulation","level":5,"score":0.32519999146461487},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2939000129699707},{"id":"https://openalex.org/C98907195","wikidata":"https://www.wikidata.org/wiki/Q5428562","display_name":"Facial motion capture","level":5,"score":0.2881999909877777},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2736999988555908},{"id":"https://openalex.org/C31487907","wikidata":"https://www.wikidata.org/wiki/Q1154597","display_name":"Polygon mesh","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2614000141620636}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/thms.2025.3640719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/thms.2025.3640719","pdf_url":null,"source":{"id":"https://openalex.org/S2476799526","display_name":"IEEE Transactions on Human-Machine Systems","issn_l":"2168-2291","issn":["2168-2291","2168-2305"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Human-Machine Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W788203010","https://openalex.org/W1709848863","https://openalex.org/W2015143272","https://openalex.org/W2017107803","https://openalex.org/W2163844242","https://openalex.org/W2338415399","https://openalex.org/W2406901294","https://openalex.org/W2463303114","https://openalex.org/W2737658251","https://openalex.org/W2739192055","https://openalex.org/W2769666294","https://openalex.org/W2804619907","https://openalex.org/W2891063225","https://openalex.org/W2946287218","https://openalex.org/W2963290645","https://openalex.org/W2963503541","https://openalex.org/W2979894294","https://openalex.org/W2981263323","https://openalex.org/W3015814181","https://openalex.org/W3015873132","https://openalex.org/W3025521275","https://openalex.org/W3034211329","https://openalex.org/W3081192838","https://openalex.org/W3081492798","https://openalex.org/W3083131369","https://openalex.org/W3083394627","https://openalex.org/W3094411524","https://openalex.org/W3094612121","https://openalex.org/W3109585842","https://openalex.org/W3154411171","https://openalex.org/W3186090335","https://openalex.org/W3197859103","https://openalex.org/W3211147706","https://openalex.org/W4200630629","https://openalex.org/W4205222302","https://openalex.org/W4221142137","https://openalex.org/W4303448003","https://openalex.org/W4309995325","https://openalex.org/W4312095900","https://openalex.org/W4312495146","https://openalex.org/W4312959196","https://openalex.org/W4321020813"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1,140],"in":[2,56],"speech-driven":[3,80],"facial":[4,81,92],"animation":[5,49,82,149,159],"have":[6],"attracted":[7],"significant":[8],"interest":[9],"across":[10,40],"computer":[11],"graphics,":[12],"human\u2013computer":[13],"interaction":[14],"systems,":[15],"and":[16,44,58,103,127,158],"immersive":[17],"virtual":[18,146],"reality":[19],"applications.":[20],"However,":[21],"existing":[22,136],"methods":[23],"remain":[24],"constrained":[25],"by":[26,132],"dependencies":[27],"on":[28,95],"specific":[29],"reference":[30],"videos":[31],"or":[32,90],"proprietary":[33],"face":[34],"mesh":[35],"structures,":[36],"limiting":[37],"their":[38],"applicability":[39],"diverse":[41],"production":[42,143],"pipelines":[43],"reducing":[45],"compatibility":[46,153],"with":[47,110,154],"industry-standard":[48],"workflows.":[50],"To":[51],"overcome":[52],"these":[53],"fundamental":[54],"limitations":[55],"generalization":[57],"deployment":[59],"flexibility,":[60],"we":[61],"propose":[62],"Speech2Blend\u2014an":[63],"end-to-end":[64],"hybrid":[65],"convolutional-recurrent":[66],"network":[67],"that":[68],"directly":[69],"learns":[70],"nonlinear":[71],"speech-to-blendshape":[72],"parameter":[73],"mappings.":[74],"This":[75],"novel":[76],"approach":[77],"enables":[78],"markerless":[79],"generation":[83],"without":[84],"restrictive":[85],"inputs":[86],"like":[87],"video":[88],"references":[89],"specialized":[91],"rigs.":[93],"Trained":[94],"the":[96],"largest":[97],"available":[98],"digital":[99],"human":[100,147],"dataset":[101],"(BEAT)":[102],"rigorously":[104],"evaluated":[105],"using":[106],"three":[107],"benchmark":[108],"datasets":[109],"photorealistic":[111],"visualization":[112],"tools,":[113],"Speech2Blend":[114],"achieves":[115],"state-of-the-art":[116],"performance.":[117],"It":[118],"delivers":[119],"superior":[120],"audio-visual":[121],"synchronization":[122],"through":[123],"learned":[124],"temporal":[125],"dynamics":[126],"reduces":[128],"lip":[129],"vertex":[130],"error":[131],"30%":[133],"compared":[134],"to":[135],"baseline":[137],"methods.":[138],"These":[139],"significantly":[141],"lower":[142],"costs":[144],"for":[145],"speech":[148],"while":[150],"enabling":[151],"cross-platform":[152],"common":[155],"game":[156],"engines":[157],"software.":[160]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-22T00:00:00"}