{"id":"https://openalex.org/W4389665966","doi":"https://doi.org/10.1109/iros55552.2023.10342027","title":"Co-Speech Gesture Synthesis using Discrete Gesture Token Learning","display_name":"Co-Speech Gesture Synthesis using Discrete Gesture Token Learning","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389665966","doi":"https://doi.org/10.1109/iros55552.2023.10342027"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10342027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5058214616","display_name":"Shuhong Lu","orcid":"https://orcid.org/0000-0003-3493-8163"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuhong Lu","raw_affiliation_strings":["Institute for Creative Technolo-gies, University of Southern California,Los Angeles,USA","Institute for Creative Technolo-gies, University of Southern California, Los Angeles, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Creative Technolo-gies, University of Southern California,Los Angeles,USA","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I4210087747"]},{"raw_affiliation_string":"Institute for Creative Technolo-gies, University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I4210087747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045112037","display_name":"Youngwoo Yoon","orcid":"https://orcid.org/0000-0003-4286-3421"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngwoo Yoon","raw_affiliation_strings":["Electronics and Telecommunications Research Institute,Daejeon,Republic of Korea","Electronics and Telecommunications Research Institute, Daejeon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I142401562"]},{"raw_affiliation_string":"Electronics and Telecommunications Research Institute, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066604966","display_name":"Andrew Feng","orcid":"https://orcid.org/0000-0002-1675-745X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Feng","raw_affiliation_strings":["Institute for Creative Technolo-gies, University of Southern California,Los Angeles,USA","Institute for Creative Technolo-gies, University of Southern California, Los Angeles, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Creative Technolo-gies, University of Southern California,Los Angeles,USA","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I4210087747"]},{"raw_affiliation_string":"Institute for Creative Technolo-gies, University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I4210087747"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9808","last_page":"9815"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9998000264167786,"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":0.9998000264167786,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9997000098228455,"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/T12290","display_name":"Human Motion and Animation","score":0.9975000023841858,"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":0.8956121802330017},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7772359848022461},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6683549284934998},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5535328388214111},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5365064144134521},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.5196419954299927},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.49723485112190247},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47327351570129395},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4501051604747772},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44455772638320923},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4371757507324219},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.41003286838531494},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3368105888366699},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10018295049667358}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8956121802330017},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7772359848022461},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6683549284934998},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5535328388214111},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5365064144134521},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.5196419954299927},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.49723485112190247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47327351570129395},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4501051604747772},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44455772638320923},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4371757507324219},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.41003286838531494},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3368105888366699},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10018295049667358},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10342027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321681","display_name":"Ministry of Trade, Industry and Energy","ror":"https://ror.org/008nkqk13"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1499739753","https://openalex.org/W2024536104","https://openalex.org/W2493916176","https://openalex.org/W2792764867","https://openalex.org/W2949924544","https://openalex.org/W2962730651","https://openalex.org/W2962795401","https://openalex.org/W2963799213","https://openalex.org/W2967443589","https://openalex.org/W2971074500","https://openalex.org/W2978956737","https://openalex.org/W2982625143","https://openalex.org/W3002310794","https://openalex.org/W3009042479","https://openalex.org/W3083173864","https://openalex.org/W3124346429","https://openalex.org/W3125087480","https://openalex.org/W3125775899","https://openalex.org/W3133090439","https://openalex.org/W3152733922","https://openalex.org/W3153551559","https://openalex.org/W3180355996","https://openalex.org/W3181695292","https://openalex.org/W3188493377","https://openalex.org/W3192902592","https://openalex.org/W3194872882","https://openalex.org/W3205306934","https://openalex.org/W3207098744","https://openalex.org/W4230429791","https://openalex.org/W4287802874","https://openalex.org/W4301206121","https://openalex.org/W4304616951","https://openalex.org/W4312674262","https://openalex.org/W4312719027","https://openalex.org/W4312974539","https://openalex.org/W4321351659","https://openalex.org/W6629789113","https://openalex.org/W6677003812","https://openalex.org/W6749825310","https://openalex.org/W6762931180","https://openalex.org/W6765779288","https://openalex.org/W6776218486","https://openalex.org/W6790978476","https://openalex.org/W6793801364","https://openalex.org/W6842633604"],"related_works":["https://openalex.org/W4200502108","https://openalex.org/W2902873204","https://openalex.org/W2185750513","https://openalex.org/W3016124757","https://openalex.org/W4312416068","https://openalex.org/W3147379364","https://openalex.org/W2010878661","https://openalex.org/W2026258298","https://openalex.org/W3204639664","https://openalex.org/W2970836791"],"abstract_inverted_index":{"Synthesizing":[0],"realistic":[1,198],"co-speech":[2,55],"gestures":[3],"is":[4,58,141,159,194],"an":[5],"important":[6],"and":[7,23,40,47,82,181,193,199],"yet":[8],"unsolved":[9],"problem":[10],"for":[11,67],"creating":[12],"believable":[13],"motions":[14,66],"that":[15,59],"can":[16,76],"drive":[17],"a":[18,91,122,136],"humanoid":[19],"robot":[20],"to":[21,94,120,143,196],"interact":[22],"communicate":[24],"with":[25],"human":[26,38],"users.":[27],"Such":[28],"capability":[29],"will":[30,41],"improve":[31],"the":[32,35,54,68,79,104,117,133,145,157,171,182,186,190],"impressions":[33],"of":[34,126,148],"robots":[36],"by":[37,102],"users":[39],"find":[42],"applications":[43],"in":[44,52,99,116],"education,":[45],"training,":[46],"medical":[48],"services.":[49],"One":[50],"challenge":[51],"learning":[53],"gesture":[56,65,100,105,127,165,201],"model":[57,93,140],"there":[60],"may":[61,83],"be":[62,168],"multiple":[63,164],"viable":[64],"same":[69,172],"speech":[70,154,173],"utterance.":[71],"The":[72,178],"deterministic":[73],"regression":[74],"methods":[75,192],"not":[77],"resolve":[78],"conflicting":[80],"samples":[81],"produce":[84],"over-smoothed":[85],"or":[86],"damped":[87],"motions.":[88,202],"We":[89],"proposed":[90,187],"two-stage":[92],"address":[95],"this":[96],"uncertainty":[97],"issue":[98],"synthesis":[101],"modeling":[103],"segments":[106],"as":[107,161],"discrete":[108,123],"latent":[109],"codes.":[110],"Our":[111],"method":[112,188],"utilizes":[113],"RQ-":[114],"VAE":[115],"first":[118],"stage":[119],"learn":[121,144],"codebook":[124],"consisting":[125],"tokens":[128],"from":[129],"training":[130],"data.":[131],"In":[132],"second":[134],"stage,":[135],"two-level":[137],"autoregressive":[138],"transformer":[139],"used":[142],"prior":[146],"distribution":[147],"residual":[149],"codes":[150],"conditioned":[151],"on":[152],"input":[153,174],"context.":[155],"Since":[156],"inference":[158],"formulated":[160],"token":[162],"sampling,":[163],"sequences":[166],"could":[167],"generated":[169],"given":[170],"using":[175],"top-k":[176],"sampling.":[177],"quantitative":[179],"results":[180],"user":[183],"study":[184],"showed":[185],"outperforms":[189],"previous":[191],"able":[195],"generate":[197],"diverse":[200]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
