{"id":"https://openalex.org/W4387969394","doi":"https://doi.org/10.1145/3581783.3611779","title":"Rethinking Voice-Face Correlation: A Geometry View","display_name":"Rethinking Voice-Face Correlation: A Geometry View","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969394","doi":"https://doi.org/10.1145/3581783.3611779"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611779","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3611779","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611779","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611779","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092414567","display_name":"Xiang Li","orcid":"https://orcid.org/0000-0002-3282-1159"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Li","raw_affiliation_strings":["CMU, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3282-1159","affiliations":[{"raw_affiliation_string":"CMU, Pittsburgh, PA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070584981","display_name":"Yandong Wen","orcid":"https://orcid.org/0000-0001-6330-7438"},"institutions":[{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yandong Wen","raw_affiliation_strings":["MPI-IS, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0001-6330-7438","affiliations":[{"raw_affiliation_string":"MPI-IS, Munich, Germany","institution_ids":["https://openalex.org/I4210135521"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012381843","display_name":"Muqiao Yang","orcid":"https://orcid.org/0000-0001-6273-0138"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Muqiao Yang","raw_affiliation_strings":["CMU, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6273-0138","affiliations":[{"raw_affiliation_string":"CMU, Pittsburgh, PA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jinglu Wang","orcid":"https://orcid.org/0000-0002-3222-6579"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinglu Wang","raw_affiliation_strings":["Microsoft, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3222-6579","affiliations":[{"raw_affiliation_string":"Microsoft, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102775511","display_name":"Rita Singh","orcid":"https://orcid.org/0000-0003-3743-0162"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rita Singh","raw_affiliation_strings":["CMU, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0003-3743-0162","affiliations":[{"raw_affiliation_string":"CMU, Pittsburgh, PA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113017615","display_name":"Bhiksha Raj","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhiksha Raj","raw_affiliation_strings":["CMU & MBZUAI, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0038-5513","affiliations":[{"raw_affiliation_string":"CMU & MBZUAI, Pittsburgh, PA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4846,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72996805,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2458","last_page":"2467"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9886999726295471,"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":0.9861000180244446,"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/face","display_name":"Face (sociological concept)","score":0.6765520572662354},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6607217788696289},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5722314715385437},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.4765896499156952},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4371722340583801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41111502051353455},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38164958357810974},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.26112425327301025},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18088477849960327},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07474738359451294}],"concepts":[{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6765520572662354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6607217788696289},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5722314715385437},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.4765896499156952},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4371722340583801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41111502051353455},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38164958357810974},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.26112425327301025},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18088477849960327},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07474738359451294},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611779","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3611779","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611779","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581783.3611779","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3611779","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611779","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387969394.pdf","grobid_xml":"https://content.openalex.org/works/W4387969394.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W2008133390","https://openalex.org/W2011040757","https://openalex.org/W2022554507","https://openalex.org/W2057355542","https://openalex.org/W2085999891","https://openalex.org/W2086233528","https://openalex.org/W2102152293","https://openalex.org/W2134113392","https://openalex.org/W2140312704","https://openalex.org/W2160126058","https://openalex.org/W2237250383","https://openalex.org/W2403957496","https://openalex.org/W2488426223","https://openalex.org/W2509287279","https://openalex.org/W2569657992","https://openalex.org/W2593898237","https://openalex.org/W2599621350","https://openalex.org/W2794922094","https://openalex.org/W2884460600","https://openalex.org/W2914217321","https://openalex.org/W2937977583","https://openalex.org/W2963081548","https://openalex.org/W2963290645","https://openalex.org/W2964052309","https://openalex.org/W2972778435","https://openalex.org/W2979157532","https://openalex.org/W2981263323","https://openalex.org/W3036167779","https://openalex.org/W3096831136","https://openalex.org/W3110123653","https://openalex.org/W3127573699","https://openalex.org/W3163527109","https://openalex.org/W3166609825","https://openalex.org/W4221144911","https://openalex.org/W4312933868","https://openalex.org/W4372260342","https://openalex.org/W6600005967","https://openalex.org/W6600210589","https://openalex.org/W6779823529"],"related_works":["https://openalex.org/W2149537132","https://openalex.org/W2018871932","https://openalex.org/W641279757","https://openalex.org/W370975646","https://openalex.org/W1670566515","https://openalex.org/W4242022592","https://openalex.org/W596972243","https://openalex.org/W4313230280","https://openalex.org/W69751022","https://openalex.org/W2063534752"],"abstract_inverted_index":{"Previous":[0],"works":[1],"on":[2,19,108,148],"voice-face":[3,149],"matching":[4],"and":[5,14,27,69,87,98,117,121,128,140,151],"voice-guided":[6],"face":[7,75,88,101,115,133],"synthesis":[8],"demonstrate":[9],"strong":[10],"correlations":[11,125],"between":[12,126],"voice":[13,45,68,86,119,127],"face,":[15],"but":[16],"mainly":[17],"rely":[18],"coarse":[20],"semantic":[21,52],"cues":[22],"such":[23,135],"as":[24,80,136,154],"gender,":[25],"age,":[26],"emotion.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32,90,122],"aim":[33],"to":[34,72,83],"investigate":[35],"the":[36,40,67,85,93,100,132,137],"capability":[37],"of":[38,95,131],"reconstructing":[39],"3D":[41,74,114],"facial":[42,64],"shape":[43],"from":[44,46,66],"a":[47,56,81,145,155],"geometry":[48,102],"perspective":[49,147],"without":[50],"any":[51],"information.":[53],"We":[54],"propose":[55],"voice-anthropometric":[57],"measurement":[58],"(AM)-face":[59],"paradigm,":[60],"which":[61],"identifies":[62],"predictable":[63],"AMs":[65,79,97],"uses":[70],"them":[71],"guide":[73],"reconstruction.":[76],"By":[77],"leveraging":[78],"proxy":[82],"link":[84],"geometry,":[89,134],"can":[91,152],"eliminate":[92],"influence":[94],"unpredictable":[96],"make":[99],"tractable.":[103],"Our":[104,142],"approach":[105],"is":[106],"evaluated":[107],"our":[109],"proposed":[110],"dataset":[111],"with":[112],"ground-truth":[113],"scans":[116],"corresponding":[118],"recordings,":[120],"find":[123],"significant":[124],"specific":[129],"parts":[130],"nasal":[138],"cavity":[139],"cranium.":[141],"work":[143],"offers":[144],"new":[146],"correlation":[150],"serve":[153],"good":[156],"empirical":[157],"study":[158],"for":[159],"anthropometry":[160],"science.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}