{"id":"https://openalex.org/W3194605252","doi":"https://doi.org/10.1145/3462244.3479914","title":"Integrated Speech and Gesture Synthesis","display_name":"Integrated Speech and Gesture Synthesis","publication_year":2021,"publication_date":"2021-10-15","ids":{"openalex":"https://openalex.org/W3194605252","doi":"https://doi.org/10.1145/3462244.3479914","mag":"3194605252"},"language":"en","primary_location":{"id":"doi:10.1145/3462244.3479914","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3462244.3479914","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3462244.3479914","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3462244.3479914","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Siyang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Siyang Wang","raw_affiliation_strings":["KTH Royal Institute of Technology, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Simon Alexanderson","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Simon Alexanderson","raw_affiliation_strings":["KTH Royal Institute of Technology, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Joakim Gustafson","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Joakim Gustafson","raw_affiliation_strings":["KTH Royal Institute of Technology, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jonas Beskow","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Jonas Beskow","raw_affiliation_strings":["KTH Royal Institute of Technology, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Gustav Eje Henter","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Gustav Eje Henter","raw_affiliation_strings":["KTH Royal Institute of Technology, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":null,"display_name":"\u00c9va Sz\u00e9kely","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"\u00c9va Sz\u00e9kely","raw_affiliation_strings":["KTH Royal Institute of Technology, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"177","last_page":"185"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9994999766349792,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9977999925613403,"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/gesture","display_name":"Gesture","score":0.8736000061035156},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6438000202178955},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5763000249862671},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5454999804496765},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.4147999882698059},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4002000093460083},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.3903999924659729}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8736000061035156},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7840999960899353},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6438000202178955},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6323999762535095},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5763000249862671},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5454999804496765},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.4147999882698059},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4002000093460083},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.3903999924659729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36489999294281006},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.35019999742507935},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.2727000117301941},{"id":"https://openalex.org/C130727458","wikidata":"https://www.wikidata.org/wiki/Q1639109","display_name":"Coarticulation","level":3,"score":0.26669999957084656},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2614000141620636}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3462244.3479914","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3462244.3479914","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3462244.3479914","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2108.11436","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.11436","pdf_url":"https://arxiv.org/pdf/2108.11436","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:DiVA.org:kth-313183","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-313183","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3462244.3479914","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3462244.3479914","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3462244.3479914","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3102226089","display_name":null,"funder_award_id":"P20-0298","funder_id":"https://openalex.org/F4320322659","funder_display_name":"Riksbankens Jubileumsfond"},{"id":"https://openalex.org/G5660684794","display_name":null,"funder_award_id":"P20-0298 (CAPTivating)","funder_id":"https://openalex.org/F4320322659","funder_display_name":"Riksbankens Jubileumsfond"},{"id":"https://openalex.org/G712881263","display_name":null,"funder_award_id":"2018-","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G7322658688","display_name":null,"funder_award_id":"2018-05409","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"}],"funders":[{"id":"https://openalex.org/F4320322327","display_name":"Knut och Alice Wallenbergs Stiftelse","ror":"https://ror.org/004hzzk67"},{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"},{"id":"https://openalex.org/F4320322659","display_name":"Riksbankens Jubileumsfond","ror":"https://ror.org/02jkbm893"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3194605252.pdf","grobid_xml":"https://content.openalex.org/works/W3194605252.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1208039178","https://openalex.org/W1547861087","https://openalex.org/W1969681536","https://openalex.org/W1977259876","https://openalex.org/W2007337857","https://openalex.org/W2008208299","https://openalex.org/W2024536104","https://openalex.org/W2044109807","https://openalex.org/W2078082557","https://openalex.org/W2235920218","https://openalex.org/W2515943672","https://openalex.org/W2884374054","https://openalex.org/W2901872500","https://openalex.org/W2937881934","https://openalex.org/W2945629925","https://openalex.org/W2962795401","https://openalex.org/W2963300588","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2967443589","https://openalex.org/W2972569067","https://openalex.org/W2973177710","https://openalex.org/W2981802563","https://openalex.org/W2997964553","https://openalex.org/W3002310794","https://openalex.org/W3009042479","https://openalex.org/W3015282541","https://openalex.org/W3015922793","https://openalex.org/W3016151952","https://openalex.org/W3025893035","https://openalex.org/W3042815677","https://openalex.org/W3081416955","https://openalex.org/W3083173864","https://openalex.org/W3093973228","https://openalex.org/W3098994456","https://openalex.org/W3125087480","https://openalex.org/W3133090439","https://openalex.org/W3163293525","https://openalex.org/W3198131199","https://openalex.org/W6912462253"],"related_works":[],"abstract_inverted_index":{"Text-to-speech":[0],"and":[1,18,36,64,101,123,167,186],"co-speech":[2],"gesture":[3,65,102,124,187],"synthesis":[4,66,138,165,188],"have":[5],"until":[6],"now":[7],"been":[8],"treated":[9],"as":[10,140,142,144,190],"separate":[11],"areas":[12],"by":[13],"two":[14,23,51,94],"different":[15],"research":[16],"communities,":[17],"applications":[19,120],"merely":[20],"stack":[21],"the":[22,42,50,87,98,111,135,145,174,180],"technologies":[24],"using":[25],"a":[26,54,57,71,106,191],"simple":[27],"system-level":[28],"pipeline.":[29],"This":[30],"can":[31],"lead":[32],"to":[33,47,81,160,173],"modeling":[34],"inefficiencies":[35],"may":[37],"introduce":[38],"inconsistencies":[39],"that":[40,109,130],"limit":[41],"achievable":[43],"naturalness.":[44],"We":[45,68,85],"propose":[46,70],"instead":[48],"synthesize":[49],"modalities":[52],"in":[53,89,103,118,152],"single":[55],"model,":[56],"new":[58],"problem":[59],"we":[60,149],"call":[61],"integrated":[62,137],"speech":[63,100,122,185],"(ISG).":[67],"also":[69],"set":[72],"of":[73,95,134,179,183],"models":[74,88,112,139],"modified":[75],"from":[76],"state-of-the-art":[77,146],"neural":[78],"speech-synthesis":[79],"engines":[80],"achieve":[82,161],"this":[83,162],"goal.":[84],"evaluate":[86,97],"three":[90,154],"carefully-designed":[91],"user":[92],"studies,":[93],"which":[96],"synthesized":[99],"isolation,":[104],"plus":[105],"combined":[107],"study":[108],"evaluates":[110],"like":[113],"they":[114],"will":[115],"be":[116],"used":[117],"real-world":[119],"\u2013":[121],"presented":[125],"together.":[126],"The":[127,156],"results":[128],"show":[129],"participants":[131],"rate":[132],"one":[133],"proposed":[136],"being":[141],"good":[143],"pipeline":[147,175],"system":[148],"compare":[150],"against,":[151],"all":[153],"tests.":[155],"model":[157],"is":[158],"able":[159],"with":[163],"faster":[164],"time":[166],"greatly":[168],"reduced":[169],"parameter":[170],"count":[171],"compared":[172],"system,":[176],"illustrating":[177],"some":[178],"potential":[181],"benefits":[182],"treating":[184],"together":[189],"single,":[192],"unified":[193],"problem.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2021-08-30T00:00:00"}