{"id":"https://openalex.org/W4396768801","doi":"https://doi.org/10.1016/j.neucom.2024.127831","title":"Learning hierarchical discrete prior for co-speech gesture generation","display_name":"Learning hierarchical discrete prior for co-speech gesture generation","publication_year":2024,"publication_date":"2024-05-09","ids":{"openalex":"https://openalex.org/W4396768801","doi":"https://doi.org/10.1016/j.neucom.2024.127831"},"language":"en","primary_location":{"id":"doi:10.1016/j.neucom.2024.127831","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neucom.2024.127831","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.neucom.2024.127831","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056625731","display_name":"Jian Zhang","orcid":"https://orcid.org/0000-0002-2591-7929"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Jian Zhang","raw_affiliation_strings":["Waseda University, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057487414","display_name":"Osamu Yoshie","orcid":"https://orcid.org/0000-0002-4192-554X"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Osamu Yoshie","raw_affiliation_strings":["Waseda University, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5056625731"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":{"value":2470,"currency":"USD","value_usd":2470},"apc_paid":{"value":2470,"currency":"USD","value_usd":2470},"fwci":0.7501,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6640968,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"595","issue":null,"first_page":"127831","last_page":"127831"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.996999979019165,"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":0.8633421659469604},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.8619115352630615},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7879495024681091},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5835964679718018},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5541964769363403},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.4611629843711853},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4566901624202728},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39045247435569763},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3659467101097107},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.30701684951782227}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8633421659469604},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.8619115352630615},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7879495024681091},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5835964679718018},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5541964769363403},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.4611629843711853},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4566901624202728},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39045247435569763},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3659467101097107},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30701684951782227}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.neucom.2024.127831","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neucom.2024.127831","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.neucom.2024.127831","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neucom.2024.127831","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W2901285216","https://openalex.org/W2945629925","https://openalex.org/W2962770929","https://openalex.org/W2962795401","https://openalex.org/W2963799213","https://openalex.org/W2971074500","https://openalex.org/W2978956737","https://openalex.org/W2983429428","https://openalex.org/W3025893035","https://openalex.org/W3036601975","https://openalex.org/W3042815677","https://openalex.org/W3083173864","https://openalex.org/W3091564954","https://openalex.org/W3107914916","https://openalex.org/W3125277150","https://openalex.org/W3125775899","https://openalex.org/W3166762869","https://openalex.org/W3172764674","https://openalex.org/W3173897458","https://openalex.org/W3194872882","https://openalex.org/W3197411683","https://openalex.org/W4221142137","https://openalex.org/W4230429791","https://openalex.org/W4241614188","https://openalex.org/W4245804068","https://openalex.org/W4280528743","https://openalex.org/W4285081118","https://openalex.org/W4301914798","https://openalex.org/W4303448003","https://openalex.org/W4304080460","https://openalex.org/W4312674262","https://openalex.org/W4312933868","https://openalex.org/W4385284180","https://openalex.org/W4385764101","https://openalex.org/W4386071584","https://openalex.org/W4386075984","https://openalex.org/W4386076103","https://openalex.org/W4386076137","https://openalex.org/W4386076250","https://openalex.org/W4386784289","https://openalex.org/W4389665966","https://openalex.org/W4390572877","https://openalex.org/W4400518895","https://openalex.org/W4402776467","https://openalex.org/W6755843876","https://openalex.org/W6762931180","https://openalex.org/W6769637165","https://openalex.org/W6774263716","https://openalex.org/W6780218876","https://openalex.org/W6780978430","https://openalex.org/W6781275627","https://openalex.org/W6795432927","https://openalex.org/W6852839485"],"related_works":["https://openalex.org/W2669956259","https://openalex.org/W4249005693","https://openalex.org/W3088732000","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"],"abstract_inverted_index":{"In":[0],"the":[1,19,44,61,67,73,101,122,141,158,162,170,176,185,202],"context":[2],"of":[3,57,69,124,143,161],"Co-Speech":[4],"Gesture":[5],"Generation,":[6],"Vector-Quantized":[7],"Variational":[8],"Autoencoder":[9],"(VQ-VAE)":[10],"based":[11],"methods":[12],"have":[13],"shown":[14],"promising":[15],"results":[16,174],"by":[17,42],"separating":[18],"generation":[20,94,171,196],"process":[21],"into":[22,37],"two":[23],"stages:":[24],"learning":[25,43,142,165],"discrete":[26,39],"gesture":[27,32,36,50,85,119,125,191,195],"priors":[28],"via":[29],"pretraining":[30,56],"for":[31,114,169],"reconstruction,":[33],"which":[34,106],"encodes":[35],"a":[38,109,198],"codebook,":[40,163],"followed":[41],"mapping":[45],"between":[46],"speech":[47],"audio":[48,154],"and":[49,83,93,117,132,146,153,178,193,206],"codebook":[51,76,112],"indices.":[52],"This":[53],"design":[54],"leverages":[55],"motion":[58,62],"VQVAE":[59],"with":[60,197],"reconstruction":[63,91,123,192],"task":[64],"to":[65,79,157],"improve":[66],"quality":[68,92],"generated":[70],"gestures.":[71],"However,":[72],"vanilla":[74],"VQVAE\u2019s":[75],"often":[77],"fails":[78],"encode":[80],"both":[81,189],"low-level":[82,118,133],"high-level":[84,116,131],"features":[86,156],"adequately,":[87],"resulting":[88],"in":[89,188],"limited":[90],"performance.":[95],"To":[96],"address":[97],"this,":[98],"we":[99],"propose":[100],"Hierarchical":[102],"Discrete":[103],"Audio-to-Gesture":[104],"(HD-A2G),":[105],"innovates":[107],"(i)":[108],"two-stage":[110],"hierarchical":[111,167],"structure":[113],"capturing":[115],"priors,":[120],"enabling":[121],"details.":[126],"(ii)":[127],"it":[128,149],"further":[129],"integrates":[130],"feature":[134],"using":[135],"an":[136],"AdaIn":[137],"layer,":[138],"effectively":[139],"enhancing":[140],"gesture\u2019s":[144],"rhythm":[145],"content.":[147],"(iii)":[148],"explicitly":[150],"maps":[151],"text":[152],"onset":[155],"appropriate":[159],"levels":[160],"ensuring":[164],"accurate":[166],"associations":[168],"stage.":[172],"Experimental":[173],"on":[175],"BEAT":[177],"Trinity":[179],"datasets":[180],"demonstrate":[181],"that":[182],"HD-A2G":[183],"outperform":[184],"baseline":[186],"method":[187],"pretrained":[190],"audio-conditioned":[194],"clear":[199],"margin,":[200],"achieving":[201],"state-of-the-art":[203],"performance":[204],"qualitatively":[205],"quantitatively.":[207]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}