{"id":"https://openalex.org/W4320166262","doi":"https://doi.org/10.48550/arxiv.2301.10047","title":"DiffMotion: Speech-Driven Gesture Synthesis Using Denoising Diffusion Model","display_name":"DiffMotion: Speech-Driven Gesture Synthesis Using Denoising Diffusion Model","publication_year":2023,"publication_date":"2023-01-24","ids":{"openalex":"https://openalex.org/W4320166262","doi":"https://doi.org/10.48550/arxiv.2301.10047"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2301.10047","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.10047","pdf_url":"https://arxiv.org/pdf/2301.10047","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2301.10047","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100403444","display_name":"Fan Zhang","orcid":"https://orcid.org/0000-0002-2594-0467"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049643712","display_name":"Naye Ji","orcid":"https://orcid.org/0000-0002-6986-3766"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji, Naye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059097674","display_name":"Fuxing Gao","orcid":"https://orcid.org/0009-0008-5586-4734"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Fuxing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108604941","display_name":"Yongping Li","orcid":"https://orcid.org/0009-0008-6716-9982"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yongping","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9973000288009644,"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":0.9973000288009644,"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/T10914","display_name":"Tactile and Sensory Interactions","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9907000064849854,"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/gesture","display_name":"Gesture","score":0.9204492568969727},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7390407919883728},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5841944813728333},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5557258129119873},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5440137386322021},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.44022274017333984},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.438819944858551},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.43093952536582947},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.42132675647735596},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.2916530668735504},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14611852169036865}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.9204492568969727},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7390407919883728},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5841944813728333},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5557258129119873},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5440137386322021},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.44022274017333984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.438819944858551},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.43093952536582947},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.42132675647735596},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2916530668735504},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14611852169036865},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2301.10047","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.10047","pdf_url":"https://arxiv.org/pdf/2301.10047","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2301.10047","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2301.10047","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2301.10047","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.10047","pdf_url":"https://arxiv.org/pdf/2301.10047","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8176539726","display_name":null,"funder_award_id":"LGF22F020008","funder_id":"https://openalex.org/F4320338465","funder_display_name":"Zhejiang Province Public Welfare Technology Application Research Project"}],"funders":[{"id":"https://openalex.org/F4320338465","display_name":"Zhejiang Province Public Welfare Technology Application Research Project","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4320166262.pdf","grobid_xml":"https://content.openalex.org/works/W4320166262.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2902873204","https://openalex.org/W2185750513","https://openalex.org/W2028966255","https://openalex.org/W2010878661","https://openalex.org/W3147379364","https://openalex.org/W2026258298","https://openalex.org/W2466763065","https://openalex.org/W3204639664","https://openalex.org/W2970836791","https://openalex.org/W1994032303"],"abstract_inverted_index":{"Speech-driven":[0],"gesture":[1,54,140],"synthesis":[2,55],"is":[3,17],"a":[4,14,51,69,91,98,102],"field":[5],"of":[6,80,135],"growing":[7],"interest":[8],"in":[9],"virtual":[10],"human":[11],"creation.":[12],"However,":[13],"critical":[15],"challenge":[16],"the":[18,77,81,107,111,133],"inherent":[19],"intricate":[20],"one-to-many":[21],"mapping":[22],"between":[23],"speech":[24,82],"and":[25,31,68,84,105,118,128,131],"gestures.":[26,86],"Previous":[27],"studies":[28],"have":[29],"explored":[30],"achieved":[32],"significant":[33],"progress":[34],"with":[35,115],"generative":[36],"models.":[37,60],"Notwithstanding,":[38],"most":[39],"synthetic":[40],"gestures":[41,108],"are":[42],"still":[43],"vastly":[44],"less":[45],"natural.":[46],"This":[47],"paper":[48],"presents":[49],"DiffMotion,":[50],"novel":[52],"speech-driven":[53,139],"architecture":[56],"based":[57],"on":[58,138],"diffusion":[59,71,88],"The":[61,74,87],"model":[62],"comprises":[63],"an":[64],"autoregressive":[65],"temporal":[66,78],"encoder":[67,75],"denoising":[70],"probability":[72],"Module.":[73],"extracts":[76],"context":[79],"input":[83],"historical":[85],"module":[89],"learns":[90],"parameterized":[92],"Markov":[93],"chain":[94],"to":[95,110],"gradually":[96],"convert":[97],"simple":[99],"distribution":[100,104],"into":[101],"complex":[103],"generates":[106],"according":[109],"accompanied":[112],"speech.":[113],"Compared":[114],"baselines,":[116],"objective":[117],"subjective":[119],"evaluations":[120],"confirm":[121],"that":[122],"our":[123],"approach":[124],"can":[125],"produce":[126],"natural":[127],"diverse":[129],"gesticulation":[130],"demonstrate":[132],"benefits":[134],"diffusion-based":[136],"models":[137],"synthesis.":[141]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}