{"id":"https://openalex.org/W4375869333","doi":"https://doi.org/10.1109/icassp49357.2023.10095304","title":"Salient Co-Speech Gesture Synthesizing with Discrete Motion Representation","display_name":"Salient Co-Speech Gesture Synthesizing with Discrete Motion Representation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869333","doi":"https://doi.org/10.1109/icassp49357.2023.10095304"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5025863422","display_name":"Zijie Ye","orcid":"https://orcid.org/0009-0003-3741-0118"},"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":"Zijie Ye","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100405579","display_name":"Jia Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I29955533","display_name":"Center for Information Technology","ror":"https://ror.org/03jh5a977","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I29955533"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Jia Jia","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084","Beijing National Research Center for Information Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology","institution_ids":["https://openalex.org/I29955533"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017383334","display_name":"Haozhe Wu","orcid":"https://orcid.org/0000-0002-3036-6930"},"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":"Haozhe Wu","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047669397","display_name":"Shuo Huang","orcid":"https://orcid.org/0000-0002-0054-8880"},"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":"Shuo Huang","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073997389","display_name":"Shikun Sun","orcid":null},"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":"Shikun Sun","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076090670","display_name":"Junliang Xing","orcid":"https://orcid.org/0000-0001-6801-0510"},"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":"Junliang Xing","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]}],"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9952999949455261,"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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9951000213623047,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.7060396671295166},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7055832147598267},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.6932665109634399},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6405056118965149},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5480688810348511},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49738791584968567},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4648512899875641},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3692331314086914},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3461466431617737}],"concepts":[{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.7060396671295166},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7055832147598267},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.6932665109634399},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6405056118965149},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5480688810348511},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49738791584968567},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4648512899875641},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3692331314086914},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3461466431617737},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4300000071525574}],"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":25,"referenced_works":["https://openalex.org/W153699105","https://openalex.org/W2194775991","https://openalex.org/W2235920218","https://openalex.org/W2747874407","https://openalex.org/W2752796333","https://openalex.org/W2780124704","https://openalex.org/W2901285216","https://openalex.org/W2962795401","https://openalex.org/W2962896489","https://openalex.org/W2963781481","https://openalex.org/W2964325361","https://openalex.org/W3002310794","https://openalex.org/W3009042479","https://openalex.org/W3021636956","https://openalex.org/W3083173864","https://openalex.org/W3102619627","https://openalex.org/W3102725307","https://openalex.org/W3125775899","https://openalex.org/W3154411171","https://openalex.org/W3163293525","https://openalex.org/W4230429791","https://openalex.org/W4293363567","https://openalex.org/W6739901393","https://openalex.org/W6948150082","https://openalex.org/W6996224657"],"related_works":["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","https://openalex.org/W1974473538","https://openalex.org/W2020010749","https://openalex.org/W2796116650"],"abstract_inverted_index":{"Synthesizing":[0],"co-speech":[1,41,61,115,162,167],"gestures":[2,42],"is":[3,12],"challenging":[4],"because":[5],"the":[6,81,85,101,131,147,187],"mapping":[7,83],"from":[8,195],"speech":[9,132],"to":[10,79,180,185],"gesticulation":[11],"inherently":[13],"non-deterministic.":[14],"When":[15],"giving":[16],"talks,":[17],"people":[18],"conduct":[19],"not":[20],"only":[21],"gentle":[22],"and":[23,29,43,84,99,139],"rhythmic":[24],"motions":[25],"but":[26],"also":[27,174],"abrupt":[28],"salient":[30,68,142,158,171,182,188],"gesticulations.":[31,69,172],"Most":[32],"previous":[33],"research":[34],"efforts,":[35],"however,":[36],"ignore":[37],"this":[38,55],"nature":[39],"of":[40,91],"synthesize":[44],"deterministic":[45],"results,":[46],"producing":[47],"over-smoothed":[48],"movements":[49],"with":[50,119,146,170],"limited":[51],"expressiveness.":[52],"To":[53],"address":[54],"issue,":[56],"we":[57,71,110,151],"propose":[58],"a":[59,73,112,153,165,176],"new":[60,154,177],"gesture":[62,86,116,168],"generation":[63,87],"approach":[64,197],"that":[65],"produces":[66,140],"high-quality":[67],"Specifically,":[70],"build":[72],"discrete":[74],"motion":[75,97,159,183,189],"representation":[76],"(DMR)":[77],"space":[78,98],"bridge":[80],"speech-gesture":[82,105],"stages.":[88],"The":[89],"incorporation":[90],"DMR":[92],"enables":[93],"random":[94],"sampling":[95],"in":[96,104,144,161],"avoids":[100],"over-smooth":[102],"problem":[103],"mapping.":[106],"Based":[107],"on":[108,130],"DMR,":[109],"devise":[111],"novel":[113],"multi-modal":[114],"synthesis":[117],"model":[118],"temporal":[120],"attention":[121],"(MCGT).":[122],"MCGT":[123],"explicitly":[124],"models":[125],"DMR\u2019s":[126],"categorical":[127],"distribution":[128],"conditioned":[129],"context,":[133],"which":[134],"captures":[135],"complex":[136],"context":[137],"patterns":[138],"more":[141],"gesticulations":[143],"sync":[145],"context.":[148],"In":[149],"addition,":[150],"construct":[152],"benchmark":[155],"for":[156],"evaluating":[157],"quality":[160],"gestures,":[163],"containing":[164],"large-scale":[166],"dataset":[169],"We":[173],"introduce":[175],"metric,":[178],"referred":[179],"as":[181],"similarity,":[184],"evaluate":[186],"quality.":[190],"Experiments":[191],"demonstrate":[192],"superior":[193],"results":[194],"our":[196],"over":[198],"several":[199],"competing":[200],"baselines.":[201]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}