{"id":"https://openalex.org/W4408351991","doi":"https://doi.org/10.1109/icassp49660.2025.10890615","title":"Identity-Preserving Audio-Driven Holistic Human Motion Video Generation","display_name":"Identity-Preserving Audio-Driven Holistic Human Motion Video Generation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408351991","doi":"https://doi.org/10.1109/icassp49660.2025.10890615"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890615","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5102788950","display_name":"Haiwei Xue","orcid":"https://orcid.org/0000-0001-7318-9682"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haiwei Xue","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043901952","display_name":"Zhensong Zhang","orcid":"https://orcid.org/0009-0001-7911-7564"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhensong Zhang","raw_affiliation_strings":["Huawei Noah&#x2019;s Ark Lab,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x2019;s Ark Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100780133","display_name":"Minglei Li","orcid":"https://orcid.org/0000-0001-5432-2855"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minglei Li","raw_affiliation_strings":["01.AI,Beijing,China"],"affiliations":[{"raw_affiliation_string":"01.AI,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103105111","display_name":"Zonghong Dai","orcid":"https://orcid.org/0009-0006-7723-4130"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zonghong Dai","raw_affiliation_strings":["Institute of Fudan University,Artificial Intelligence Innovation and Incubation (Al&#x2019;),Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Institute of Fudan University,Artificial Intelligence Innovation and Incubation (Al&#x2019;),Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102788950"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.2205,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.76143467,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"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/T12290","display_name":"Human Motion and Animation","score":0.9873999953269958,"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"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9873999953269958,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9807999730110168,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9728000164031982,"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/computer-science","display_name":"Computer science","score":0.6269788146018982},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5227891802787781},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.43134886026382446},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3757800757884979},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3553942143917084},{"id":"https://openalex.org/keywords/aesthetics","display_name":"Aesthetics","score":0.12032526731491089},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.09110823273658752}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6269788146018982},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5227891802787781},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.43134886026382446},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3757800757884979},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3553942143917084},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.12032526731491089},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.09110823273658752}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890615","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W2007337857","https://openalex.org/W2008208299","https://openalex.org/W2027222744","https://openalex.org/W2062165658","https://openalex.org/W2114770744","https://openalex.org/W2133665775","https://openalex.org/W2727071501","https://openalex.org/W2765811365","https://openalex.org/W2946584893","https://openalex.org/W2963800363","https://openalex.org/W3083173864","https://openalex.org/W3109875893","https://openalex.org/W3193427204","https://openalex.org/W4312933868","https://openalex.org/W4364377334","https://openalex.org/W4385764101","https://openalex.org/W4386066256","https://openalex.org/W4386075487","https://openalex.org/W4386075767","https://openalex.org/W4386075984","https://openalex.org/W4389665966","https://openalex.org/W4390094952","https://openalex.org/W4390190334","https://openalex.org/W4390874168","https://openalex.org/W4392305749","https://openalex.org/W4393154834","https://openalex.org/W4399206662","https://openalex.org/W4402704505","https://openalex.org/W4402704510","https://openalex.org/W4402716313","https://openalex.org/W4402727180","https://openalex.org/W4402754063","https://openalex.org/W4402754210","https://openalex.org/W4403780835","https://openalex.org/W4404719810","https://openalex.org/W4405466653","https://openalex.org/W6640963894","https://openalex.org/W6753914649","https://openalex.org/W6764925396","https://openalex.org/W6766759079","https://openalex.org/W6774314701","https://openalex.org/W6791353385","https://openalex.org/W6842124410","https://openalex.org/W6847123917","https://openalex.org/W6854511533","https://openalex.org/W6858385707","https://openalex.org/W6872369781"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Generating":[0],"realistic":[1],"human":[2,64,160],"motion":[3,65,161],"videos":[4,66,148],"is":[5],"a":[6,57,91,153],"pivotal":[7],"challenge":[8],"in":[9],"advancing":[10],"human-computer":[11],"interaction.":[12],"While":[13],"existing":[14],"approaches":[15],"often":[16],"focus":[17],"on":[18],"generating":[19],"either":[20],"head":[21],"or":[22],"gesture":[23],"movements":[24],"from":[25,67],"audio,":[26],"they":[27],"lack":[28],"unified":[29],"control":[30],"over":[31],"full-body":[32],"motion,":[33],"frequently":[34],"producing":[35],"low-resolution":[36],"and":[37,78,104,114,126,134,155],"blurred":[38],"outputs.":[39],"Additionally,":[40],"these":[41],"methods":[42],"struggle":[43],"to":[44,81],"maintain":[45],"character":[46,86,124],"identity":[47,71,98,125],"throughout":[48,128],"the":[49,83,109,121,129,132,137],"generated":[50,138],"content.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55],"introduce":[56],"novel":[58],"framework":[59,145],"that":[60,143],"generates":[61],"photorealistic,":[62],"personalized":[63],"audio":[68],"by":[69],"decoupling":[70],"features.":[72],"We":[73],"integrate":[74],"both":[75],"visual":[76],"features":[77],"voice":[79],"timbre":[80],"enhance":[82],"preservation":[84],"of":[85,112,123,136],"identity.":[87],"Our":[88],"approach":[89,118],"follows":[90],"four-stage":[92],"paradigm:":[93],"(1)":[94],"frame":[95],"generation,":[96],"(2)":[97],"feature":[99],"customization,":[100],"(3)":[101],"audio-motion":[102,113],"modeling,":[103],"(4)":[105],"motion-video":[106,115],"rendering.":[107],"Through":[108],"collaborative":[110],"modeling":[111],"stages,":[116],"our":[117,144],"effectively":[119],"maintains":[120],"consistency":[122],"background":[127],"video,":[130],"enhancing":[131],"realism":[133],"coherence":[135],"video.":[139],"Experimental":[140],"results":[141],"demonstrate":[142],"delivers":[146],"high-resolution":[147],"with":[149],"superior":[150],"fidelity,":[151],"establishing":[152],"new":[154],"effective":[156],"baseline":[157],"for":[158],"holistic":[159],"video":[162],"generation.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-28T08:17:26.163206","created_date":"2025-10-10T00:00:00"}
