{"id":"https://openalex.org/W4402548919","doi":"https://doi.org/10.1145/3686215.3688819","title":"Towards interpretable co-speech gestures synthesis using STARGATE","display_name":"Towards interpretable co-speech gestures synthesis using STARGATE","publication_year":2024,"publication_date":"2024-10-30","ids":{"openalex":"https://openalex.org/W4402548919","doi":"https://doi.org/10.1145/3686215.3688819"},"language":"en","primary_location":{"id":"doi:10.1145/3686215.3688819","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3686215.3688819","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 26th International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3686215.3688819","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032406017","display_name":"Louis Abel","orcid":"https://orcid.org/0009-0009-6799-8008"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Louis Abel","raw_affiliation_strings":["Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, F-54000, France"],"raw_orcid":"https://orcid.org/0009-0009-6799-8008","affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, F-54000, France","institution_ids":["https://openalex.org/I4210121838","https://openalex.org/I90183372","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039712983","display_name":"Vincent Colotte","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Vincent Colotte","raw_affiliation_strings":["Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, F-54000, France","MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (France)"],"raw_orcid":"https://orcid.org/0009-0000-5040-6971","affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, F-54000, France","institution_ids":["https://openalex.org/I4210121838","https://openalex.org/I90183372","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044130608","display_name":"Slim Ouni","orcid":"https://orcid.org/0000-0001-5286-7368"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Slim Ouni","raw_affiliation_strings":["Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, F-54000, France"],"raw_orcid":"https://orcid.org/0000-0001-5286-7368","affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, F-54000, France","institution_ids":["https://openalex.org/I4210121838","https://openalex.org/I90183372","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5032406017"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210121838","https://openalex.org/I90183372"],"apc_list":null,"apc_paid":null,"fwci":0.3432,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59156328,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"138","last_page":"146"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9975000023841858,"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/T11285","display_name":"Hearing Impairment and Communication","score":0.9947999715805054,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.8553484082221985},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6822496652603149},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6639454364776611},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5140210390090942},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41695988178253174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4029238224029541}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8553484082221985},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6822496652603149},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6639454364776611},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5140210390090942},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41695988178253174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4029238224029541}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3686215.3688819","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3686215.3688819","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 26th International Conference on Multimodal Interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04678537v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04678537v1/file/Towards_interpretable_co_speech_gestures_synthesis_using_STARGATE_final.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"International Conference on Multimodal Interaction (ICMI Companion \u201924: GENEA Workshop), Nov 2024, San Jos\u00e9, Costa Rica. ⟨10.1145/3686215.3688819⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"doi:10.1145/3686215.3688819","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3686215.3688819","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 26th International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W591589697","https://openalex.org/W1498883201","https://openalex.org/W1977259876","https://openalex.org/W1988585419","https://openalex.org/W2034356075","https://openalex.org/W2169262156","https://openalex.org/W2612744935","https://openalex.org/W2727071501","https://openalex.org/W2747874407","https://openalex.org/W2793569032","https://openalex.org/W2922298118","https://openalex.org/W2945629925","https://openalex.org/W3002310794","https://openalex.org/W3083173864","https://openalex.org/W3099073275","https://openalex.org/W3107914916","https://openalex.org/W3125775899","https://openalex.org/W3133090439","https://openalex.org/W3153551559","https://openalex.org/W3195319595","https://openalex.org/W4221142137","https://openalex.org/W4230429791","https://openalex.org/W4303448003","https://openalex.org/W4361755841","https://openalex.org/W4377010269","https://openalex.org/W4386655536","https://openalex.org/W4401307826"],"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/W3204019825"],"abstract_inverted_index":{"Co-speech":[0],"gestures":[1,44,120,139],"synthesis":[2],"is":[3,45,115],"a":[4,54,101],"growing":[5],"field":[6],"of":[7,68,117],"research.":[8],"However,":[9],"new":[10],"systems":[11],"often":[12],"use":[13],"complex":[14],"or":[15,28],"heavy":[16],"architecture,":[17],"making":[18],"them":[19],"unsuitable":[20],"for":[21,29,57],"incorporation":[22],"into":[23],"Embodied":[24],"Conversational":[25],"Agents":[26],"(ECAs)":[27],"interpretation":[30],"in":[31,104,121],"other":[32],"research":[33],"fields":[34],"such":[35],"as":[36,125],"linguistics,":[37],"where":[38],"the":[39,122],"link":[40],"between":[41],"speech":[42],"and":[43,89,93,107],"difficult":[46],"to":[47,70,83],"investigate":[48],"manually.":[49],"This":[50],"paper":[51],"presents":[52],"STARGATE,":[53],"novel":[55],"architecture":[56],"Spatio-Temporal":[58],"Autoregressive":[59],"Graph":[60],"from":[61,140],"Audio-Text":[62],"Embeddings.":[63],"The":[64,96],"model":[65,97,103,114,136],"takes":[66],"advantage":[67],"autoregression":[69],"provide":[71],"fast":[72],"generation":[73],"capabilities.":[74],"Additionally,":[75],"it":[76],"employs":[77],"graph":[78],"convolutions":[79],"coupled":[80],"with":[81],"attention":[82],"incorporate":[84],"explicit":[85],"structural":[86],"prior":[87],"knowledge":[88],"enable":[90],"efficient":[91],"spatial":[92],"temporal":[94],"processing.":[95],"was":[98],"evaluated":[99],"against":[100],"state-of-the-art":[102],"both":[105],"perceptive":[106],"quantitative":[108],"studies.":[109],"We":[110],"demonstrated":[111],"that":[112,132],"our":[113,135],"capable":[116],"generating":[118],"convincing":[119],"same":[123],"range":[124],"state-of-the-art.":[126],"Furthermore,":[127],"we":[128],"conducted":[129],"in-depth":[130],"analysis":[131],"show":[133],"how":[134],"actually":[137],"produces":[138],"its":[141],"input.":[142]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}