{"id":"https://openalex.org/W7131265578","doi":"https://doi.org/10.1109/vcip67698.2025.11396896","title":"Transparent System For Lightweight Neural Talking Faces","display_name":"Transparent System For Lightweight Neural Talking Faces","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W7131265578","doi":"https://doi.org/10.1109/vcip67698.2025.11396896"},"language":null,"primary_location":{"id":"doi:10.1109/vcip67698.2025.11396896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip67698.2025.11396896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Visual Communications and Image Processing (VCIP)","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/A5119832397","display_name":"Oskar Bartosz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119410","display_name":"Institute of Fundamental Technological Research","ror":"https://ror.org/03fs4aq04","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210119410","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Oskar Bartosz","raw_affiliation_strings":["Polish Academy of Sciences,Samsung R&D Institute Poland & Institute of Fundamental Technological Research,Warsaw,Poland,02-105"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Polish Academy of Sciences,Samsung R&D Institute Poland & Institute of Fundamental Technological Research,Warsaw,Poland,02-105","institution_ids":["https://openalex.org/I4210119410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126709054","display_name":"\u0141ukasz Daba\u0142a","orcid":null},"institutions":[{"id":"https://openalex.org/I108403487","display_name":"Warsaw University of Technology","ror":"https://ror.org/00y0xnp53","country_code":"PL","type":"education","lineage":["https://openalex.org/I108403487"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"\u0141ukasz Daba\u0142a","raw_affiliation_strings":["Warsaw University Of Technology,Warsaw,Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Warsaw University Of Technology,Warsaw,Poland","institution_ids":["https://openalex.org/I108403487"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055852189","display_name":"Janusz B\u0119dkowski","orcid":"https://orcid.org/0000-0003-2630-1947"},"institutions":[{"id":"https://openalex.org/I4210119410","display_name":"Institute of Fundamental Technological Research","ror":"https://ror.org/03fs4aq04","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210119410","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Janusz Bedkowski","raw_affiliation_strings":["Polish Academy of Sciences,Samsung R&D Institute Poland & Institute of Fundamental Technological Research,Warsaw,Poland,02-105"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Polish Academy of Sciences,Samsung R&D Institute Poland & Institute of Fundamental Technological Research,Warsaw,Poland,02-105","institution_ids":["https://openalex.org/I4210119410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.69772015,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.10740000009536743,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10320","display_name":"Neural Networks and Applications","score":0.10740000009536743,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.04919999837875366,"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/T11347","display_name":"Neural Networks Stability and Synchronization","score":0.044599998742341995,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/rendering","display_name":"Rendering (computer graphics)","score":0.7750999927520752},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5277000069618225},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5163000226020813},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.37389999628067017},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.36970001459121704},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3571000099182129},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.3544999957084656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8427000045776367},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.7750999927520752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6146000027656555},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5972999930381775},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5277000069618225},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5163000226020813},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.37389999628067017},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.36970001459121704},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3684999942779541},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3571000099182129},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3544999957084656},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3483999967575073},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34470000863075256},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.31310001015663147},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.2815000116825104},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C89720835","wikidata":"https://www.wikidata.org/wiki/Q1531701","display_name":"Global illumination","level":3,"score":0.26179999113082886},{"id":"https://openalex.org/C36816356","wikidata":"https://www.wikidata.org/wiki/Q16911860","display_name":"3D rendering","level":3,"score":0.2583000063896179},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vcip67698.2025.11396896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip67698.2025.11396896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2884460600","https://openalex.org/W2990452356","https://openalex.org/W3081492798","https://openalex.org/W3095664976","https://openalex.org/W3097792222","https://openalex.org/W3138516171","https://openalex.org/W3154411171","https://openalex.org/W4200630629","https://openalex.org/W4312671791","https://openalex.org/W4390872769","https://openalex.org/W4394597549","https://openalex.org/W4403081627","https://openalex.org/W4415968771"],"related_works":[],"abstract_inverted_index":{"Lip":[0],"synchronization":[1],"from":[2,38,49,64],"voice":[3],"is":[4,155],"a":[5,65,115,172],"challenging":[6],"task":[7],"in":[8,75,167],"audiovisual":[9],"synthesis,":[10],"often":[11],"solved":[12],"using":[13],"large":[14],"neural":[15,78,124,174],"architectures":[16],"with":[17,114,122,141,162,199],"millions":[18],"of":[19,46,80],"parameters.":[20],"In":[21,120],"this":[22,168],"paper,":[23],"we":[24,170],"propose":[25],"an":[26],"extremely":[27],"lightweight":[28,192],"and":[29,55,68],"modular":[30],"method":[31,154],"for":[32,160,179,202],"generating":[33],"speech-driven":[34],"facial":[35,47],"landmarks":[36,63,185],"(visemes)":[37],"audio":[39,69],"features.":[40],"Our":[41],"approach":[42],"separates":[43],"the":[44,123,142,150,184],"modeling":[45],"motion":[48,132],"image":[50,67],"generation,":[51],"enabling":[52],"fast,":[53],"interpretable,":[54],"extensible":[56],"systems.The":[57],"proposed":[58],"system":[59],"induces":[60],"knowledge":[61],"about":[62],"single":[66],"data,":[70],"to":[71,149,182],"be":[72,196],"further":[73],"used":[74],"conditioning":[76],"fast":[77],"renders":[79],"talking":[81,204],"faces.":[82],"Solution":[83],"converts":[84],"Mel-Frequency":[85],"Cepstral":[86],"Coefficients":[87],"(MFCCs)":[88],"into":[89,98,186],"compact":[90],"latent":[91],"mouth":[92,131],"encodings,":[93],"which":[94],"are":[95],"then":[96],"decoded":[97],"dynamic":[99],"2D":[100],"landmark":[101],"sequences.":[102],"The":[103],"model":[104],"achieves":[105],"real-time":[106,203],"performance":[107],"at":[108,133],"over":[109],"500":[110],"landmark-frames":[111],"per":[112,136],"second,":[113],"total":[116],"size":[117],"under":[118],"20KB.":[119],"connection":[121],"rendering":[125,164,201],"module,":[126],"it":[127],"produces":[128],"smooth,":[129],"realistic":[130],"30":[134],"frames":[135],"second":[137],"that":[138,191],"aligns":[139],"well":[140],"input":[143],"speech":[144],"signal":[145],"after":[146],"being":[147],"rendered.Thanks":[148],"transparent":[151],"design,":[152],"our":[153],"easily":[156],"explainable.":[157],"Modularity":[158],"allows":[159],"integration":[161],"various":[163],"backends":[165],"-":[166],"work,":[169],"use":[171],"high-fidelity":[173],"face":[175,205],"renderer":[176],"originally":[177],"developed":[178],"deepfake":[180],"synthesis":[181],"convert":[183],"full-resolution":[187],"images.":[188],"This":[189],"demonstrates":[190],"viseme":[193],"generation":[194],"can":[195],"effectively":[197],"combined":[198],"photorealistic":[200],"applications.":[206]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-02-25T00:00:00"}