{"id":"https://openalex.org/W7164838287","doi":"https://doi.org/10.1145/3805622.3810854","title":"Decoupling Vocal and Rhythmic Conditioning for Music-Driven Singing Avatar Animation","display_name":"Decoupling Vocal and Rhythmic Conditioning for Music-Driven Singing Avatar Animation","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164838287","doi":"https://doi.org/10.1145/3805622.3810854"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810854","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810854","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810854","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111241673","display_name":"Yiguo Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Yiguo Jiang","raw_affiliation_strings":["University of Macau, Macau, Macao"],"raw_orcid":"https://orcid.org/0009-0005-9336-8123","affiliations":[{"raw_affiliation_string":"University of Macau, Macau, Macao","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058799911","display_name":"Xiaodong Cun","orcid":"https://orcid.org/0000-0003-3607-2236"},"institutions":[{"id":"https://openalex.org/I4396570619","display_name":"Great Bay University","ror":"https://ror.org/01hdgge16","country_code":null,"type":"education","lineage":["https://openalex.org/I4396570619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong Cun","raw_affiliation_strings":["Great Bay University, Dongguan, China"],"raw_orcid":"https://orcid.org/0000-0003-3607-2236","affiliations":[{"raw_affiliation_string":"Great Bay University, Dongguan, China","institution_ids":["https://openalex.org/I4396570619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101849245","display_name":"Chen-Bin Feng","orcid":"https://orcid.org/0009-0006-2957-2792"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Chenbin Feng","raw_affiliation_strings":["University of Macau, Macau, Macao"],"raw_orcid":"https://orcid.org/0009-0006-2957-2792","affiliations":[{"raw_affiliation_string":"University of Macau, Macau, Macao","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101425421","display_name":"Jian Sun","orcid":"https://orcid.org/0000-0001-6270-2698"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Jian Sun","raw_affiliation_strings":["University of Macau, Macau, Macao"],"raw_orcid":"https://orcid.org/0000-0001-6270-2698","affiliations":[{"raw_affiliation_string":"University of Macau, Macau, Macao","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005772506","display_name":"Chi\u2010Man Pun","orcid":"https://orcid.org/0000-0003-1788-3746"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Chi-Man Pun","raw_affiliation_strings":["University of Macau, Macau, Macao"],"raw_orcid":"https://orcid.org/0000-0003-1788-3746","affiliations":[{"raw_affiliation_string":"University of Macau, Macau, Macao","institution_ids":["https://openalex.org/I204512498"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2314","last_page":"2322"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.7020999789237976,"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":0.7020999789237976,"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":0.17419999837875366,"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":0.054099999368190765,"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/singing","display_name":"Singing","score":0.8628000020980835},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.6685000061988831},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.576200008392334},{"id":"https://openalex.org/keywords/avatar","display_name":"Avatar","score":0.5586000084877014},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.5370000004768372},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.4925000071525574},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.44690001010894775}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8628000020980835},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6708999872207642},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.6685000061988831},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.576200008392334},{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.5586000084877014},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.5370000004768372},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.4925000071525574},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.44690001010894775},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.444599986076355},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43950000405311584},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.3824999928474426},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C130727458","wikidata":"https://www.wikidata.org/wiki/Q1639109","display_name":"Coarticulation","level":3,"score":0.35749998688697815},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.33889999985694885},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32829999923706055},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C60115397","wikidata":"https://www.wikidata.org/wiki/Q5188732","display_name":"Crossmodal","level":4,"score":0.29820001125335693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2797999978065491},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2757999897003174}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810854","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810854","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810854","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810854","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2134963900","https://openalex.org/W2604379605","https://openalex.org/W2962785568","https://openalex.org/W2963081548","https://openalex.org/W2973049979","https://openalex.org/W3019952993","https://openalex.org/W3081492798","https://openalex.org/W3106759947","https://openalex.org/W3186090335","https://openalex.org/W4281730245","https://openalex.org/W4312671789","https://openalex.org/W4312933868","https://openalex.org/W4380994134","https://openalex.org/W4382469130","https://openalex.org/W4386066404","https://openalex.org/W4386072021","https://openalex.org/W4386075487","https://openalex.org/W4387682247","https://openalex.org/W4389212256","https://openalex.org/W4389383543","https://openalex.org/W4390872742","https://openalex.org/W4390872769","https://openalex.org/W4390874181","https://openalex.org/W4394597549","https://openalex.org/W4399344807","https://openalex.org/W4402093509","https://openalex.org/W4402980762","https://openalex.org/W4403938273","https://openalex.org/W4404199654","https://openalex.org/W4409369524","https://openalex.org/W4410028535","https://openalex.org/W4415114166","https://openalex.org/W4415366882"],"related_works":[],"abstract_inverted_index":{"Synthetic":[0],"media":[1],"generation":[2],"is":[3],"a":[4,106,123,153],"burgeoning":[5],"field":[6],"in":[7,18,94],"multimedia":[8],"research.":[9],"While":[10],"audio-driven":[11],"avatar":[12,24],"animation":[13,25,38],"has":[14],"garnered":[15],"significant":[16],"attention":[17,126],"digital":[19],"entertainment,":[20],"yet":[21,168],"music-driven":[22],"singing":[23,37,48,113,133,146,197],"remains":[26],"relatively":[27],"underexplored":[28],"due":[29],"to":[30,86,148,162],"its":[31],"unique":[32],"challenges.":[33],"Distinct":[34],"from":[35,144,159],"speech,":[36],"necessitates":[39],"the":[40,88,130,145,160],"simultaneous":[41],"modeling":[42],"of":[43,91,132],"lip":[44,150,174],"articulation":[45],"governed":[46],"by":[47],"vocal,":[49],"and":[50,70,82,135,176,194],"global":[51],"facial":[52,97,164,178],"dynamics":[53],"synchronized":[54,196],"with":[55],"musical":[56],"rhythm.":[57],"Existing":[58],"methods":[59],"typically":[60],"rely":[61],"on":[62,117],"3D":[63,118],"intermediate":[64],"representations,":[65],"which":[66],"impose":[67],"geometric":[68],"constraints":[69],"often":[71],"degrade":[72],"visual":[73],"details.":[74],"Furthermore,":[75],"some":[76],"approaches":[77],"that":[78,109,128,172,188],"simply":[79],"concatenate":[80],"vocal":[81,142],"BGM":[83,161],"features":[84],"fail":[85],"capture":[87],"distinct":[89],"roles":[90,131],"these":[92,101],"signals":[93],"driving":[95],"specific":[96],"regions.":[98],"To":[99],"address":[100],"limitations,":[102],"we":[103,121],"propose":[104],"MusicAvatar,":[105],"diffusion-based":[107],"framework":[108],"directly":[110],"synthesizes":[111],"2D":[112],"avatars":[114],"without":[115,183],"relying":[116],"priors.":[119],"Moreover,":[120],"design":[122,170],"dual-stream":[124],"music":[125],"module":[127],"decouples":[129],"voice":[134],"BGM.":[136],"Specifically,":[137],"one":[138],"cross-attention":[139],"stream":[140,155],"extracts":[141],"cues":[143],"track":[147],"drive":[149],"movements,":[151],"while":[152],"parallel":[154,167],"captures":[156],"rhythmic":[157,177],"patterns":[158],"modulate":[163],"motion.":[165],"This":[166],"synergistic":[169],"ensures":[171],"precise":[173],"movement":[175],"motion":[179],"are":[180],"modeled":[181],"explicitly":[182],"interference.":[184],"Extensive":[185],"experiments":[186],"demonstrate":[187],"MusicAvatar":[189],"generates":[190],"highly":[191],"natural,":[192],"expressive,":[193],"rhythmically":[195],"avatars,":[198],"outperforming":[199],"state-of-the-art":[200],"approaches.":[201]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-06-16T00:00:00"}
