{"id":"https://openalex.org/W4403922699","doi":"https://doi.org/10.1145/3686215.3688823","title":"Benchmarking Speech-Driven Gesture Generation Models for Generalization to Unseen Voices and Noisy Environments","display_name":"Benchmarking Speech-Driven Gesture Generation Models for Generalization to Unseen Voices and Noisy Environments","publication_year":2024,"publication_date":"2024-10-30","ids":{"openalex":"https://openalex.org/W4403922699","doi":"https://doi.org/10.1145/3686215.3688823"},"language":"en","primary_location":{"id":"doi:10.1145/3686215.3688823","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3686215.3688823","pdf_url":null,"source":null,"license":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111233555","display_name":"J. I. Gomez Sanchez","orcid":"https://orcid.org/0009-0008-0468-6659"},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Johsac Isbac Gomez Sanchez","raw_affiliation_strings":["Depto. de Engenharia de Computa\u00e7\u00e3o e Automa\u00e7\u00e3o (DCA), Faculdade de Engenharia El\u00e9trica e de Computa\u00e7\u00e3o (FEEC), Universidade Estadual de Campinas (UNICAMP), Brazil"],"raw_orcid":"https://orcid.org/0009-0008-0468-6659","affiliations":[{"raw_affiliation_string":"Depto. de Engenharia de Computa\u00e7\u00e3o e Automa\u00e7\u00e3o (DCA), Faculdade de Engenharia El\u00e9trica e de Computa\u00e7\u00e3o (FEEC), Universidade Estadual de Campinas (UNICAMP), Brazil","institution_ids":["https://openalex.org/I181391015"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114468466","display_name":"Kevin Adier Inofuente Colque","orcid":null},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Kevin Adier Inofuente Colque","raw_affiliation_strings":["Depto. de Engenharia de Computa\u00e7\u00e3o e Automa\u00e7\u00e3o (DCA), Faculdade de Engenharia El\u00e9trica e de Computa\u00e7\u00e3o (FEEC), Universidade Estadual de Campinas (UNICAMP), Brazil"],"raw_orcid":"https://orcid.org/0009-0001-6349-6379","affiliations":[{"raw_affiliation_string":"Depto. de Engenharia de Computa\u00e7\u00e3o e Automa\u00e7\u00e3o (DCA), Faculdade de Engenharia El\u00e9trica e de Computa\u00e7\u00e3o (FEEC), Universidade Estadual de Campinas (UNICAMP), Brazil","institution_ids":["https://openalex.org/I181391015"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073917855","display_name":"Leonardo B. de M. M. Marques","orcid":"https://orcid.org/0000-0002-8821-4972"},"institutions":[{"id":"https://openalex.org/I4210090141","display_name":"Centre for Research and Development in Telecommunications (Brazil)","ror":"https://ror.org/00ej99c12","country_code":"BR","type":"company","lineage":["https://openalex.org/I4210090141"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Leonardo Boulitreau de Menezes Martins Marques","raw_affiliation_strings":["CPQD, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-8821-4972","affiliations":[{"raw_affiliation_string":"CPQD, Brazil","institution_ids":["https://openalex.org/I4210090141"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047253278","display_name":"Paula Dornhofer Paro Costa","orcid":"https://orcid.org/0000-0002-1534-5744"},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Paula Dornhofer Paro Costa","raw_affiliation_strings":["Depto. de Engenharia de Computa\u00e7\u00e3o e Automa\u00e7\u00e3o (DCA), Faculdade de Engenharia El\u00e9trica e de Computa\u00e7\u00e3o (FEEC), Universidade Estadual de Campinas (UNICAMP), Brazil"],"raw_orcid":"https://orcid.org/0000-0002-1534-5744","affiliations":[{"raw_affiliation_string":"Depto. de Engenharia de Computa\u00e7\u00e3o e Automa\u00e7\u00e3o (DCA), Faculdade de Engenharia El\u00e9trica e de Computa\u00e7\u00e3o (FEEC), Universidade Estadual de Campinas (UNICAMP), Brazil","institution_ids":["https://openalex.org/I181391015"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043095306","display_name":"Rodolfo Luis Tonoli","orcid":"https://orcid.org/0000-0002-5800-654X"},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Rodolfo Luis Tonoli","raw_affiliation_strings":["Depto. de Engenharia de Computa\u00e7\u00e3o e Automa\u00e7\u00e3o (DCA), Faculdade de Engenharia El\u00e9trica e de Computa\u00e7\u00e3o (FEEC), Universidade Estadual de Campinas (UNICAMP), Brazil"],"raw_orcid":"https://orcid.org/0000-0002-5800-654X","affiliations":[{"raw_affiliation_string":"Depto. de Engenharia de Computa\u00e7\u00e3o e Automa\u00e7\u00e3o (DCA), Faculdade de Engenharia El\u00e9trica e de Computa\u00e7\u00e3o (FEEC), Universidade Estadual de Campinas (UNICAMP), Brazil","institution_ids":["https://openalex.org/I181391015"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5111233555"],"corresponding_institution_ids":["https://openalex.org/I181391015"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16748047,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"170","last_page":"174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9991999864578247,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.996399998664856,"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/T10860","display_name":"Speech and Audio Processing","score":0.9933000206947327,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.8295124769210815},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7308940887451172},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7260067462921143},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.673882007598877},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6257555484771729},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5138292908668518},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4498639404773712},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4313165545463562},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0640750527381897}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8295124769210815},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7308940887451172},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7260067462921143},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.673882007598877},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6257555484771729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5138292908668518},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4498639404773712},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4313165545463562},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0640750527381897},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3686215.3688823","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3686215.3688823","pdf_url":null,"source":null,"license":null,"license_id":null,"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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2696967604","https://openalex.org/W2914911817","https://openalex.org/W2962788625","https://openalex.org/W2962795401","https://openalex.org/W2962866891","https://openalex.org/W3015805741","https://openalex.org/W3083173864","https://openalex.org/W3115266783","https://openalex.org/W3125775899","https://openalex.org/W3163573274","https://openalex.org/W3197358873","https://openalex.org/W3209984917","https://openalex.org/W3210530853","https://openalex.org/W4285345683","https://openalex.org/W4372337821","https://openalex.org/W4386270206","https://openalex.org/W4387421378","https://openalex.org/W4387446360","https://openalex.org/W4387574681","https://openalex.org/W4392904562","https://openalex.org/W4392910552","https://openalex.org/W4395096406"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2000169967","https://openalex.org/W4399363378"],"abstract_inverted_index":{"Speech-driven":[0],"gesture":[1,57],"generation":[2,58],"models":[3,21,59,145],"enhance":[4],"robot":[5],"gestures":[6,15],"and":[7,45,63,135],"control":[8],"avatars":[9],"in":[10,34,39,115,156],"virtual":[11],"environments":[12],"by":[13],"synchronizing":[14],"with":[16,30,132],"speech":[17,76],"prosody.":[18],"However,":[19],"state-of-the-art":[20,124],"are":[22],"trained":[23],"on":[24],"a":[25,51,69,82,93,109,128],"limited":[26],"number":[27],"of":[28,85],"speakers,":[29],"audios":[31],"typically":[32],"recorded":[33],"controlled":[35,94],"conditions,":[36,152],"potentially":[37],"resulting":[38],"poor":[40],"generalization":[41,88],"to":[42,73,98,122,150],"new":[43],"voices":[44,62,134],"noisy":[46,96],"environments.":[47],"This":[48,106],"paper":[49],"presents":[50],"robust":[52],"evaluation":[53,114],"method":[54],"for":[55,112,144],"speech-driven":[56],"against":[60],"unseen":[61],"varying":[64],"noise":[65,104],"levels.":[66],"We":[67],"utilize":[68],"voice":[70],"conversion":[71],"model":[72,100,126],"produce":[74],"synthetic":[75,95],"that":[77,146],"maintains":[78],"prosodic":[79],"features,":[80],"ensuring":[81,153],"thorough":[83],"test":[84],"the":[86,123,142],"model\u2019s":[87],"capabilities.":[89],"Additionally,":[90],"we":[91],"introduce":[92],"dataset":[97],"evaluate":[99],"performance":[101,130,155],"under":[102],"different":[103],"conditions.":[105],"methodology":[107],"establishes":[108],"comprehensive":[110],"framework":[111],"robustness":[113],"speech-to-gesture":[116],"synthesis":[117],"benchmarks.":[118],"Applying":[119],"this":[120],"approach":[121],"DiffuseStyleGesture+":[125],"reveals":[127],"slight":[129],"degradation":[131],"diverse":[133],"increased":[136],"background":[137],"noise.":[138],"Our":[139],"findings":[140],"emphasize":[141],"need":[143],"can":[147],"generalize":[148],"better":[149],"real-world":[151],"reliable":[154],"varied":[157],"acoustic":[158],"scenarios.":[159]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}