{"id":"https://openalex.org/W3106759947","doi":"https://doi.org/10.1145/3410700.3425435","title":"Song2Face: Synthesizing Singing Facial Animation from Audio","display_name":"Song2Face: Synthesizing Singing Facial Animation from Audio","publication_year":2020,"publication_date":"2020-11-17","ids":{"openalex":"https://openalex.org/W3106759947","doi":"https://doi.org/10.1145/3410700.3425435","mag":"3106759947"},"language":"en","primary_location":{"id":"doi:10.1145/3410700.3425435","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3410700.3425435","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIGGRAPH Asia 2020 Technical Communications","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/A5036602757","display_name":"Shohei Iwase","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shohei Iwase","raw_affiliation_strings":["Waseda University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102744164","display_name":"Takuya Kato","orcid":"https://orcid.org/0000-0001-7952-4752"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuya Kato","raw_affiliation_strings":["ExaWizards Inc. Waseda University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ExaWizards Inc. Waseda University","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013288881","display_name":"Shugo Yamaguchi","orcid":"https://orcid.org/0009-0001-6369-3540"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shugo Yamaguchi","raw_affiliation_strings":["Waseda University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102379122","display_name":"Yukitaka Tsuchiya","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tsuchiya Yukitaka","raw_affiliation_strings":["Waseda University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083427215","display_name":"Shigeo Morishima","orcid":"https://orcid.org/0000-0001-8859-6539"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shigeo Morishima","raw_affiliation_strings":["Waseda Research Institute for Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda Research Institute for Science and Engineering","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.3287,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.51447091,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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/T11448","display_name":"Face recognition and analysis","score":0.9991999864578247,"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":0.9983000159263611,"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/singing","display_name":"Singing","score":0.8955333828926086},{"id":"https://openalex.org/keywords/vibrato","display_name":"Vibrato","score":0.8951613903045654},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7423383593559265},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.708113431930542},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.6469524502754211},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.618410050868988},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.45060113072395325},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4306855797767639},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3451598286628723},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.3208703398704529},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.180095374584198},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.07299584150314331}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8955333828926086},{"id":"https://openalex.org/C2781100714","wikidata":"https://www.wikidata.org/wiki/Q377435","display_name":"Vibrato","level":3,"score":0.8951613903045654},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7423383593559265},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.708113431930542},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.6469524502754211},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.618410050868988},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.45060113072395325},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4306855797767639},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3451598286628723},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.3208703398704529},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.180095374584198},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.07299584150314331},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3410700.3425435","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3410700.3425435","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIGGRAPH Asia 2020 Technical Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5004185486","display_name":"Analysis of Reality Distorted Spatio-Temporal Field to Improve Human Skill and Motivation","funder_award_id":"19H01129","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1554803342","https://openalex.org/W2071096833","https://openalex.org/W2468212864","https://openalex.org/W2737658251","https://openalex.org/W2739192055","https://openalex.org/W2804619907","https://openalex.org/W2949281321"],"related_works":["https://openalex.org/W2082155001","https://openalex.org/W2373880408","https://openalex.org/W405661683","https://openalex.org/W2532856746","https://openalex.org/W238390473","https://openalex.org/W2119168266","https://openalex.org/W4230480656","https://openalex.org/W2978145617","https://openalex.org/W2108382268","https://openalex.org/W2097873655"],"abstract_inverted_index":{"We":[0],"present":[1],"Song2Face,":[2],"a":[3,72,77],"deep":[4],"neural":[5],"network":[6,23,59,74,119],"capable":[7,121],"of":[8,16,61,122,128,135],"producing":[9,123],"singing":[10,17,35,40,112,158],"facial":[11,32,85],"animation":[12,93],"from":[13,69,111],"an":[14,62],"input":[15],"voice":[18,113],"and":[19,49,71,131,153],"singer":[20,78,151],"label.":[21],"The":[22],"architecture":[24],"is":[25,120],"built":[26],"upon":[27],"our":[28,58],"insight":[29],"that,":[30],"although":[31],"expression":[33,143],"when":[34],"varies":[36],"between":[37,144],"different":[38,145],"individuals,":[39],"voices":[41],"store":[42],"valuable":[43],"information":[44],"such":[45],"as":[46],"pitch,":[47],"breathe,":[48],"vibrato":[50],"that":[51,64,80,104],"expressions":[52],"may":[53],"be":[54,108,161],"attributed":[55],"to.":[56],"Therefore,":[57],"consists":[60],"encoder":[63],"extracts":[65],"relevant":[66],"vocal":[67,105],"features":[68,106],"audio,":[70],"regression":[73],"conditioned":[75],"on":[76],"label":[79],"predicts":[81],"control":[82],"parameters":[83],"for":[84,125],"animation.":[86],"In":[87],"contrast":[88],"to":[89,99],"prior":[90],"audio-driven":[91],"speech":[92],"methods":[94],"which":[95],"initially":[96],"map":[97],"audio":[98],"text-level":[100],"features,":[101],"we":[102],"show":[103],"can":[107,160],"directly":[109],"learned":[110],"without":[114],"any":[115],"explicit":[116],"constraints.":[117],"Our":[118],"movements":[124],"all":[126],"parts":[127],"the":[129,136,150,155],"face":[130],"also":[132],"rotational":[133],"movement":[134],"head":[137],"itself.":[138],"Furthermore,":[139],"stylistic":[140],"differences":[141],"in":[142],"singers":[146],"are":[147],"captured":[148],"via":[149],"label,":[152],"thus":[154],"resulting":[156],"animations":[157],"style":[159],"manipulated":[162],"at":[163],"test":[164],"time.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}