{"id":"https://openalex.org/W4415350507","doi":"https://doi.org/10.1145/3746270.3760239","title":"Face the Sound: Synthesizing Listener Facial Motion from Speaker Speech","display_name":"Face the Sound: Synthesizing Listener Facial Motion from Speaker Speech","publication_year":2025,"publication_date":"2025-10-20","ids":{"openalex":"https://openalex.org/W4415350507","doi":"https://doi.org/10.1145/3746270.3760239"},"language":null,"primary_location":{"id":"doi:10.1145/3746270.3760239","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746270.3760239","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Workshop on Multimodal and Responsible Affective Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746270.3760239","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103308477","display_name":"Lownish Rai Sookha","orcid":null},"institutions":[{"id":"https://openalex.org/I119241673","display_name":"Indian Institute of Technology Ropar","ror":"https://ror.org/02qkhhn56","country_code":"IN","type":"education","lineage":["https://openalex.org/I119241673"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Lownish Rai Sookha","raw_affiliation_strings":["Indian Institute of Technology Ropar, Rupnagar, Punjab, India"],"raw_orcid":"https://orcid.org/0009-0008-1001-8884","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Ropar, Rupnagar, Punjab, India","institution_ids":["https://openalex.org/I119241673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034501904","display_name":"Shreya Ghosh","orcid":"https://orcid.org/0000-0002-2639-8374"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shreya Ghosh","raw_affiliation_strings":["The University of Queensland, Brisbane, QLD, Australia"],"raw_orcid":"https://orcid.org/0000-0002-2639-8374","affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, QLD, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033429345","display_name":"M. A. Ganaie","orcid":"https://orcid.org/0000-0002-3986-4434"},"institutions":[{"id":"https://openalex.org/I119241673","display_name":"Indian Institute of Technology Ropar","ror":"https://ror.org/02qkhhn56","country_code":"IN","type":"education","lineage":["https://openalex.org/I119241673"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"M. A. Ganaie","raw_affiliation_strings":["Indian Institute of Technology Ropar, Rupnagar, Punjab, India"],"raw_orcid":"https://orcid.org/0000-0002-3986-4434","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Ropar, Rupnagar, Punjab, India","institution_ids":["https://openalex.org/I119241673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085376429","display_name":"Abhinav Dhall","orcid":"https://orcid.org/0000-0002-2230-1440"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Abhinav Dhall","raw_affiliation_strings":["Monash University, Melbourne, VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0002-2230-1440","affiliations":[{"raw_affiliation_string":"Monash University, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030379402","display_name":"Tom Gedeon","orcid":"https://orcid.org/0000-0001-8356-4909"},"institutions":[{"id":"https://openalex.org/I205640436","display_name":"Curtin University","ror":"https://ror.org/02n415q13","country_code":"AU","type":"education","lineage":["https://openalex.org/I205640436"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tom Gedeon","raw_affiliation_strings":["Curtin University, Perth, WA, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8356-4909","affiliations":[{"raw_affiliation_string":"Curtin University, Perth, WA, Australia","institution_ids":["https://openalex.org/I205640436"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103308477"],"corresponding_institution_ids":["https://openalex.org/I119241673"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27661188,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"152","last_page":"159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9948999881744385,"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/T12290","display_name":"Human Motion and Animation","score":0.9851999878883362,"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/gesture","display_name":"Gesture","score":0.6007000207901001},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5777000188827515},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5325999855995178},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.49779999256134033},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.42669999599456787},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.41260001063346863},{"id":"https://openalex.org/keywords/decodes","display_name":"Decodes","score":0.4034000039100647},{"id":"https://openalex.org/keywords/facial-motion-capture","display_name":"Facial motion capture","score":0.3935999870300293},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.37549999356269836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6945000290870667},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.614799976348877},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.6007000207901001},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5777000188827515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5546000003814697},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5325999855995178},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.512499988079071},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.49779999256134033},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.42669999599456787},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.41260001063346863},{"id":"https://openalex.org/C2778858076","wikidata":"https://www.wikidata.org/wiki/Q5249539","display_name":"Decodes","level":3,"score":0.4034000039100647},{"id":"https://openalex.org/C98907195","wikidata":"https://www.wikidata.org/wiki/Q5428562","display_name":"Facial motion capture","level":5,"score":0.3935999870300293},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.37549999356269836},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.35910001397132874},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.3449000120162964},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.29739999771118164},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C130727458","wikidata":"https://www.wikidata.org/wiki/Q1639109","display_name":"Coarticulation","level":3,"score":0.27239999175071716},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746270.3760239","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746270.3760239","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Workshop on Multimodal and Responsible Affective Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746270.3760239","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746270.3760239","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Workshop on Multimodal and Responsible Affective Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1990723800","https://openalex.org/W2008208299","https://openalex.org/W2021382309","https://openalex.org/W2150610356","https://openalex.org/W2213313895","https://openalex.org/W2237250383","https://openalex.org/W2568303726","https://openalex.org/W2583891190","https://openalex.org/W2772447065","https://openalex.org/W2914911817","https://openalex.org/W2962701817","https://openalex.org/W2981133004","https://openalex.org/W3030528688","https://openalex.org/W3118898753","https://openalex.org/W4288099396","https://openalex.org/W4309533780","https://openalex.org/W4312309978","https://openalex.org/W4312726738","https://openalex.org/W4367047002","https://openalex.org/W4388157164","https://openalex.org/W4400582137","https://openalex.org/W4400818936","https://openalex.org/W4402660084","https://openalex.org/W4402753806","https://openalex.org/W4403792529"],"related_works":[],"abstract_inverted_index":{"Audio":[0],"driven":[1],"facial":[2,26,31,67,115],"motion":[3,27,32,68,140],"generation":[4,69],"is":[5,147],"an":[6],"active":[7],"area":[8],"of":[9,139],"research":[10],"for":[11],"dyadic":[12],"human-avatar":[13],"interface":[14],"design.":[15],"Recently,":[16],"there":[17],"has":[18],"been":[19],"a":[20,108],"significant":[21],"progress":[22],"in":[23,79,137],"translating":[24],"speaker's":[25,53,71],"to":[28,50,132],"listener's":[29],"subjective":[30],"synthesis.":[33],"Despite":[34],"the":[35,52,126],"effort,":[36],"existing":[37],"approaches":[38],"often":[39],"rely":[40],"on":[41,65,149],"multiple":[42],"modalities":[43],"(such":[44],"as":[45],"text,":[46],"audio":[47,72],"and":[48,119,142],"visual)":[49],"map":[51],"gestures":[54],"onto":[55],"appropriate":[56],"listener":[57,66],"audio-visual":[58],"responses.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63],"focus":[64],"from":[70,88],"signal":[73],"only":[74],"with":[75,97],"very":[76],"minimal":[77],"compromise":[78],"performance.":[80],"Our":[81,122],"proposed":[82,127],"method":[83],"incorporates":[84],"contextualised":[85],"speech":[86],"representations":[87,103],"W2V-BERT":[89],"through":[90],"selective":[91],"layer":[92],"utilization,":[93],"which":[94],"are":[95,104],"fused":[96],"speaker-specific":[98],"stylistic":[99],"features.":[100],"These":[101],"enriched":[102],"then":[105],"processed":[106],"by":[107],"variational":[109],"autoencoder":[110],"(VAE)":[111],"that":[112,125],"independently":[113],"decodes":[114],"expressions,":[116],"head":[117],"pose,":[118],"eye":[120],"movements.":[121],"experiments":[123],"demonstrate":[124],"model":[128,145],"achieves":[129],"performance":[130],"comparable":[131],"state-of-the-art":[133],"(SOTA)":[134],"methods,":[135],"particularly":[136],"terms":[138],"diversity":[141],"variance.":[143],"The":[144],"code":[146],"available":[148],"hrefhttps://github.com/lownish23csz0010/FaceTheSound":[150],"GitHub.":[151]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-21T00:00:00"}
