{"id":"https://openalex.org/W4408353516","doi":"https://doi.org/10.1109/icassp49660.2025.10888507","title":"XDGesture: An xLSTM-based Diffusion Model for Co-speech Gesture Generation","display_name":"XDGesture: An xLSTM-based Diffusion Model for Co-speech Gesture Generation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353516","doi":"https://doi.org/10.1109/icassp49660.2025.10888507"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888507","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888507","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":"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/A5036056631","display_name":"Zixing Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixing Zhang","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352046","display_name":"Jiajun Li","orcid":"https://orcid.org/0000-0003-2661-0950"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Li","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100372408","display_name":"Bin Wang","orcid":"https://orcid.org/0000-0003-0893-0539"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Wang","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100449908","display_name":"Yiming Liu","orcid":"https://orcid.org/0000-0002-1393-908X"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Liu","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004305313","display_name":"Huan Zhao","orcid":"https://orcid.org/0000-0001-6286-5868"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huan Zhao","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn W. Schuller","raw_affiliation_strings":["Imperial College London,GLAM,Department of Computing,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,GLAM,Department of Computing,UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11285","display_name":"Hearing Impairment and Communication","score":0.972599983215332,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.691001296043396},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.6479141712188721},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5963082313537598},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5297445058822632},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24586045742034912},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06875723600387573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.691001296043396},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.6479141712188721},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5963082313537598},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5297445058822632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24586045742034912},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06875723600387573},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888507","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888507","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1974604838","https://openalex.org/W2007337857","https://openalex.org/W2064675550","https://openalex.org/W2169262156","https://openalex.org/W2962795401","https://openalex.org/W2967443589","https://openalex.org/W2982625143","https://openalex.org/W3009042479","https://openalex.org/W3083173864","https://openalex.org/W3110095664","https://openalex.org/W3156698624","https://openalex.org/W4221142137","https://openalex.org/W4230429791","https://openalex.org/W4303448003","https://openalex.org/W4312674262","https://openalex.org/W4377010269","https://openalex.org/W4385284180","https://openalex.org/W4385764101","https://openalex.org/W4386076103","https://openalex.org/W4386270206","https://openalex.org/W4399206662","https://openalex.org/W4402703119","https://openalex.org/W4408521096","https://openalex.org/W4412100053"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2537963312","https://openalex.org/W2066003895","https://openalex.org/W2537762514","https://openalex.org/W2349788282","https://openalex.org/W577271088","https://openalex.org/W2120801881","https://openalex.org/W1982853263"],"abstract_inverted_index":{"In":[0],"multimodal":[1,52,103],"human-computer":[2],"interaction,":[3],"generating":[4],"co-speech":[5],"gestures":[6],"is":[7],"crucial":[8],"for":[9],"enhancing":[10],"interaction":[11],"naturalness":[12],"and":[13,19,70,96,110,145],"user":[14],"experience.":[15],"However,":[16],"achieving":[17],"synchronized":[18,123],"natural":[20],"gesture":[21,118,142],"sequences":[22,119],"remains":[23],"a":[24,61,66],"significant":[25],"challenge":[26],"due":[27],"to":[28],"the":[29,83,101,114],"complexity":[30],"of":[31,116,141],"modeling":[32],"temporal":[33],"dependencies":[34,107],"across":[35],"different":[36,80],"modalities.":[37],"Existing":[38],"methods":[39],"often":[40],"rely":[41],"on":[42,135],"simple":[43],"concatenation":[44],"techniques,":[45],"which":[46],"are":[47,121],"limited":[48],"in":[49,139],"effectively":[50],"handling":[51],"information.":[53],"To":[54],"address":[55],"this":[56],"issue,":[57],"we":[58],"propose":[59],"XDGesture,":[60],"diffusion-based":[62],"framework":[63],"that":[64,120,129],"integrates":[65],"Cross-Modal":[67,73],"Fusion":[68,74],"module":[69,75],"xLSTM.":[71],"The":[72],"efficiently":[76],"merges":[77],"information":[78],"from":[79],"modalities,":[81],"providing":[82],"model":[84],"with":[85,91,124,147],"rich":[86],"contextual":[87],"conditions.":[88],"Meanwhile,":[89],"xLSTM,":[90],"its":[92],"enhanced":[93],"memory":[94],"structure":[95],"exponential":[97],"gating":[98],"mechanism,":[99],"processes":[100],"fused":[102],"data,":[104],"capturing":[105],"long-range":[106],"between":[108],"speech":[109],"gestures.":[111],"This":[112],"enables":[113],"generation":[115],"high-quality":[117],"naturally":[122],"speech.":[125,148],"Experimental":[126],"results":[127],"demonstrate":[128],"XDGesture":[130],"remarkably":[131],"outperforms":[132],"existing":[133],"baselines":[134],"multiple":[136],"datasets,":[137],"particularly":[138],"terms":[140],"quality,":[143],"naturalness,":[144],"synchronization":[146]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}