{"id":"https://openalex.org/W4392902983","doi":"https://doi.org/10.1109/icassp48485.2024.10448118","title":"Gesture Generation Via Diffusion Model with Attention Mechanism","display_name":"Gesture Generation Via Diffusion Model with Attention Mechanism","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902983","doi":"https://doi.org/10.1109/icassp48485.2024.10448118"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448118","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10448118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5100443350","display_name":"Lingling Li","orcid":"https://orcid.org/0000-0002-6130-2518"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lingling Li","raw_affiliation_strings":["Sun Yat-Sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019114400","display_name":"Li Weicong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weicong Li","raw_affiliation_strings":["Sun Yat-Sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113145189","display_name":"Qiyuan Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiyuan Ding","raw_affiliation_strings":["Sun Yat-Sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086395785","display_name":"Chengpei Tang","orcid":"https://orcid.org/0000-0002-8139-6742"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chengpei Tang","raw_affiliation_strings":["Sun Yat-Sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088124671","display_name":"Keze Wang","orcid":"https://orcid.org/0000-0002-7817-8306"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keze Wang","raw_affiliation_strings":["Sun Yat-Sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":"8316","last_page":"8320"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9991999864578247,"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/T12031","display_name":"Speech and dialogue systems","score":0.9987999796867371,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9966999888420105,"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/gesture","display_name":"Gesture","score":0.9150036573410034},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8132505416870117},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5994331240653992},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48216885328292847},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4689925014972687},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.46164029836654663},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.45029234886169434},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43654578924179077},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4300358295440674},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42862969636917114},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38497695326805115},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.38343071937561035},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09513029456138611}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.9150036573410034},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8132505416870117},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5994331240653992},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48216885328292847},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4689925014972687},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.46164029836654663},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.45029234886169434},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43654578924179077},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4300358295440674},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42862969636917114},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38497695326805115},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38343071937561035},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09513029456138611},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448118","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10448118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2135431835","https://openalex.org/W2493916176","https://openalex.org/W2962795401","https://openalex.org/W3002310794","https://openalex.org/W3036167779","https://openalex.org/W3083173864","https://openalex.org/W3124346429","https://openalex.org/W3125775899","https://openalex.org/W3181695292","https://openalex.org/W3194872882","https://openalex.org/W3204221554","https://openalex.org/W4221142137","https://openalex.org/W4230312136","https://openalex.org/W4312765683","https://openalex.org/W4312933868","https://openalex.org/W4321351659","https://openalex.org/W4385245566","https://openalex.org/W4385284180","https://openalex.org/W4386075984","https://openalex.org/W4386076103","https://openalex.org/W6739901393","https://openalex.org/W6779823529"],"related_works":["https://openalex.org/W2537963312","https://openalex.org/W2902873204","https://openalex.org/W2185750513","https://openalex.org/W2010878661","https://openalex.org/W3147379364","https://openalex.org/W2026258298","https://openalex.org/W3204639664","https://openalex.org/W2970836791","https://openalex.org/W2805039731","https://openalex.org/W2989699735"],"abstract_inverted_index":{"Generating":[0],"natural":[1,107,168],"and":[2,22,39,49,52,108,138,169,174],"semantically":[3],"aligned":[4],"gestures":[5,48,77,129,171],"from":[6,78,82],"speech":[7,21,132],"remains":[8],"a":[9,44,87,104,150],"challenging":[10],"task":[11],"in":[12,27,57,133,166],"human-computer":[13],"interaction":[14],"due":[15],"to":[16],"the":[17,50,112,144,147,161,177,181],"intricate":[18],"relationship":[19],"between":[20,46],"gestures.":[23,110],"While":[24],"recent":[25],"advances":[26],"learning-based":[28],"methodologies":[29],"have":[30],"shown":[31],"progress,":[32],"they":[33],"exhibit":[34],"limitations":[35],"like":[36],"limited":[37],"diversity":[38],"fidelity,":[40],"as":[41,43],"well":[42],"mismatch":[45],"generated":[47,128],"semantic":[51,136],"emotional":[53,139],"context,":[54],"impacting":[55],"efficacy":[56,145],"conveying":[58],"information.":[59],"To":[60,141],"address":[61],"these":[62],"multifaceted":[63],"challenges,":[64],"this":[65],"study":[66],"introduces":[67],"Gesture":[68],"Diffusion":[69],"Attention":[70],"(GDA),":[71],"an":[72],"innovative":[73],"approach":[74],"for":[75,118],"generating":[76,167],"spoken":[79],"language.":[80],"Diverging":[81],"conventional":[83],"methods,":[84],"GDA":[85,165],"incorporates":[86],"sophisticated":[88],"denoising":[89],"diffusion":[90],"probability":[91,96],"module,":[92],"progressively":[93],"transforming":[94],"simplistic":[95],"distributions":[97],"into":[98],"more":[99],"complex":[100],"ones,":[101],"consequently":[102],"yielding":[103],"repertoire":[105],"of":[106,114,135,146,152,164],"diverse":[109],"Furthermore,":[111],"utilization":[113],"pretrained":[115],"fastText":[116],"models":[117],"textual":[119],"feature":[120],"extraction,":[121],"coupled":[122],"with":[123,131],"attention":[124],"mechanisms,":[125],"ensures":[126],"that":[127,172],"align":[130],"terms":[134],"content":[137],"nuances.":[140],"empirically":[142],"validate":[143],"proposed":[148],"approach,":[149],"series":[151],"rigorous":[153],"objective":[154],"experiments":[155],"were":[156],"conducted.":[157],"The":[158],"results":[159],"demonstrate":[160],"exceptional":[162],"performance":[163],"diversified":[170],"accurately":[173],"coherently":[175],"convey":[176],"intended":[178],"information,":[179],"surpassing":[180],"benchmarks":[182],"established":[183],"by":[184],"traditional":[185],"methods.":[186],"Code":[187],"is":[188],"released":[189],"at":[190],"https://github.com/LEELLL/GDA-icassp2024.":[191]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}