{"id":"https://openalex.org/W4388623205","doi":"https://doi.org/10.1109/ro-man57019.2023.10309493","title":"Speech-Gesture GAN: Gesture Generation for Robots and Embodied Agents","display_name":"Speech-Gesture GAN: Gesture Generation for Robots and Embodied Agents","publication_year":2023,"publication_date":"2023-08-28","ids":{"openalex":"https://openalex.org/W4388623205","doi":"https://doi.org/10.1109/ro-man57019.2023.10309493"},"language":"en","primary_location":{"id":"doi:10.1109/ro-man57019.2023.10309493","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man57019.2023.10309493","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"},"type":"article","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/A5100345836","display_name":"Yu Liu","orcid":"https://orcid.org/0000-0002-7325-5763"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Carson Yu Liu","raw_affiliation_strings":["University of New South Wales,Faculty of Engineering, School of Computer Science and Engineering,Sydney,NSW,Australia,2052"],"affiliations":[{"raw_affiliation_string":"University of New South Wales,Faculty of Engineering, School of Computer Science and Engineering,Sydney,NSW,Australia,2052","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032060005","display_name":"Gelareh Mohammadi","orcid":"https://orcid.org/0000-0002-8087-2241"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Gelareh Mohammadi","raw_affiliation_strings":["University of New South Wales,Faculty of Engineering, School of Computer Science and Engineering,Sydney,NSW,Australia,2052"],"affiliations":[{"raw_affiliation_string":"University of New South Wales,Faculty of Engineering, School of Computer Science and Engineering,Sydney,NSW,Australia,2052","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041567418","display_name":"Yang Song","orcid":"https://orcid.org/0000-0003-1283-1672"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yang Song","raw_affiliation_strings":["University of New South Wales,Faculty of Engineering, School of Computer Science and Engineering,Sydney,NSW,Australia,2052"],"affiliations":[{"raw_affiliation_string":"University of New South Wales,Faculty of Engineering, School of Computer Science and Engineering,Sydney,NSW,Australia,2052","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048175000","display_name":"Wafa Johal","orcid":"https://orcid.org/0000-0001-9118-0454"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wafa Johal","raw_affiliation_strings":["University of Melbourne,Faculty of Engineering and Information Technology, School of Computing Information Systems,Melbourne,VIC,Australia,3010"],"affiliations":[{"raw_affiliation_string":"University of Melbourne,Faculty of Engineering and Information Technology, School of Computing Information Systems,Melbourne,VIC,Australia,3010","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100345836"],"corresponding_institution_ids":["https://openalex.org/I31746571"],"apc_list":null,"apc_paid":null,"fwci":0.7336,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.73518768,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"405","last_page":"412"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991999864578247,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social 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/T10812","display_name":"Human Pose and Action Recognition","score":0.9959999918937683,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.8463004231452942},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.834712028503418},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7540891170501709},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5964987874031067},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.5364234447479248},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5157642364501953},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4985990524291992},{"id":"https://openalex.org/keywords/embodied-agent","display_name":"Embodied agent","score":0.4126094579696655},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.38672634959220886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3736887574195862},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32842952013015747},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.280068039894104}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8463004231452942},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.834712028503418},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7540891170501709},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5964987874031067},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.5364234447479248},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5157642364501953},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4985990524291992},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.4126094579696655},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38672634959220886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3736887574195862},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32842952013015747},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.280068039894104},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ro-man57019.2023.10309493","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man57019.2023.10309493","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W114912394","https://openalex.org/W1977259876","https://openalex.org/W2017354274","https://openalex.org/W2077223959","https://openalex.org/W2082050175","https://openalex.org/W2105902013","https://openalex.org/W2126558800","https://openalex.org/W2141125555","https://openalex.org/W2294123875","https://openalex.org/W2495266147","https://openalex.org/W2760103357","https://openalex.org/W2766709201","https://openalex.org/W2884374054","https://openalex.org/W2896457183","https://openalex.org/W2901285216","https://openalex.org/W2901872500","https://openalex.org/W2922298118","https://openalex.org/W2950510190","https://openalex.org/W2964095416","https://openalex.org/W2967443589","https://openalex.org/W2981802563","https://openalex.org/W3002310794","https://openalex.org/W3009042479","https://openalex.org/W3083173864","https://openalex.org/W3096831136","https://openalex.org/W3099073275","https://openalex.org/W3115266783","https://openalex.org/W3118288752","https://openalex.org/W3125277150","https://openalex.org/W3125775899","https://openalex.org/W3212693919","https://openalex.org/W4221142137","https://openalex.org/W4229501902","https://openalex.org/W6741832134","https://openalex.org/W6751750676","https://openalex.org/W6755207826"],"related_works":["https://openalex.org/W1601503673","https://openalex.org/W1592154258","https://openalex.org/W1527882169","https://openalex.org/W1596535966","https://openalex.org/W1487956045","https://openalex.org/W2135357356","https://openalex.org/W2185743013","https://openalex.org/W2931456277","https://openalex.org/W2119445168","https://openalex.org/W1594469132"],"abstract_inverted_index":{"Embodied":[0,154],"agents,":[1],"in":[2,39],"the":[3,43,68,89,92,102,145],"form":[4],"of":[5,47,64,147],"virtual":[6],"agents":[7,38],"or":[8],"social":[9],"robots,":[10],"are":[11],"rapidly":[12],"becoming":[13],"more":[14],"widespread.":[15],"In":[16,52,105],"human-human":[17],"interactions,":[18],"humans":[19],"use":[20],"nonverbal":[21],"behaviours":[22],"to":[23,41,107],"convey":[24],"their":[25,48],"attitudes,":[26],"feelings,":[27],"and":[28,45,71,95,98,141,153],"intentions.":[29],"Therefore,":[30],"this":[31,53],"capability":[32],"is":[33],"also":[34],"required":[35],"for":[36,151],"embodied":[37],"order":[40,106],"enhance":[42],"quality":[44],"effectiveness":[46],"interactions":[49],"with":[50,121],"humans.":[51],"paper,":[54],"we":[55,113],"propose":[56],"a":[57,77,115,130],"novel":[58],"framework":[59,150],"that":[60],"can":[61],"generate":[62],"sequences":[63],"joint":[65],"angles":[66],"from":[67,101,129,138],"speech":[69,72,103,123],"text":[70],"audio":[73,124],"utterances.":[74],"Based":[75],"on":[76],"conditional":[78],"Generative":[79],"Adversarial":[80],"Network":[81],"(GAN),":[82],"our":[83,109,148],"proposed":[84],"neural":[85,110],"network":[86,111],"model":[87],"learns":[88],"relationships":[90],"between":[91],"co-speech":[93,119],"gestures":[94,120],"both":[96,139],"semantic":[97],"acoustic":[99],"features":[100],"input.":[104],"train":[108],"model,":[112],"employ":[114],"public":[116],"dataset":[117],"containing":[118],"corresponding":[122],"utterances,":[125],"which":[126],"were":[127],"captured":[128],"single":[131],"male":[132],"native":[133],"English":[134],"speaker.":[135],"The":[136],"results":[137],"objective":[140],"subjective":[142],"evaluations":[143],"demonstrate":[144],"efficacy":[146],"gesture-generation":[149],"Robots":[152],"Agents.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}
