{"id":"https://openalex.org/W3208997387","doi":"https://doi.org/10.1145/3485441.3485647","title":"Speech-Driven Conversational Agents using Conditional Flow-VAEs","display_name":"Speech-Driven Conversational Agents using Conditional Flow-VAEs","publication_year":2021,"publication_date":"2021-10-23","ids":{"openalex":"https://openalex.org/W3208997387","doi":"https://doi.org/10.1145/3485441.3485647","mag":"3208997387"},"language":"en","primary_location":{"id":"doi:10.1145/3485441.3485647","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3485441.3485647","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"European Conference on Visual Media Production","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/A5101923852","display_name":"Sarah Taylor","orcid":"https://orcid.org/0000-0003-1299-0446"},"institutions":[{"id":"https://openalex.org/I1118541","display_name":"University of East Anglia","ror":"https://ror.org/026k5mg93","country_code":"GB","type":"education","lineage":["https://openalex.org/I1118541"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Sarah Taylor","raw_affiliation_strings":["University of East Anglia, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of East Anglia, UK","institution_ids":["https://openalex.org/I1118541"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029043105","display_name":"Jonathan Windle","orcid":"https://orcid.org/0000-0003-4985-2282"},"institutions":[{"id":"https://openalex.org/I1118541","display_name":"University of East Anglia","ror":"https://ror.org/026k5mg93","country_code":"GB","type":"education","lineage":["https://openalex.org/I1118541"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jonathan Windle","raw_affiliation_strings":["University of East Anglia, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of East Anglia, UK","institution_ids":["https://openalex.org/I1118541"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016362960","display_name":"David Greenwood","orcid":"https://orcid.org/0000-0003-1615-2036"},"institutions":[{"id":"https://openalex.org/I1118541","display_name":"University of East Anglia","ror":"https://ror.org/026k5mg93","country_code":"GB","type":"education","lineage":["https://openalex.org/I1118541"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David Greenwood","raw_affiliation_strings":["University of East Anglia, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of East Anglia, UK","institution_ids":["https://openalex.org/I1118541"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069055807","display_name":"Iain Matthews","orcid":"https://orcid.org/0009-0000-5004-2397"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Iain Matthews","raw_affiliation_strings":["Carnegie Mellon University, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, US","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101923852"],"corresponding_institution_ids":["https://openalex.org/I1118541"],"apc_list":null,"apc_paid":null,"fwci":1.4564,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.84436904,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9994999766349792,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9994999766349792,"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/T12290","display_name":"Human Motion and Animation","score":0.998199999332428,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9968000054359436,"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/autoencoder","display_name":"Autoencoder","score":0.8437837362289429},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7637486457824707},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.652245283126831},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5818034410476685},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.568679690361023},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.4520091116428375},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.44075649976730347},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.43793830275535583},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.43306106328964233},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.43095964193344116},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.42729613184928894},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4100317060947418},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36575818061828613},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3381597399711609},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10843181610107422},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.10018107295036316},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08960634469985962}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8437837362289429},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7637486457824707},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.652245283126831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5818034410476685},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.568679690361023},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.4520091116428375},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.44075649976730347},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.43793830275535583},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.43306106328964233},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.43095964193344116},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.42729613184928894},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4100317060947418},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36575818061828613},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3381597399711609},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10843181610107422},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.10018107295036316},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08960634469985962},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3485441.3485647","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3485441.3485647","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"European Conference on Visual Media Production","raw_type":"proceedings-article"},{"id":"pmh:oai:ueaeprints.uea.ac.uk:86886","is_oa":false,"landing_page_url":"https://ueaeprints.uea.ac.uk/id/eprint/86886/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400384","display_name":"UEA Digital Repository (University of East Anglia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1118541","host_organization_name":"University of East Anglia","host_organization_lineage":["https://openalex.org/I1118541"],"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":"NonPeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W1969681536","https://openalex.org/W2007337857","https://openalex.org/W2008208299","https://openalex.org/W2024536104","https://openalex.org/W2057069782","https://openalex.org/W2077206503","https://openalex.org/W2127876774","https://openalex.org/W2169262156","https://openalex.org/W2405774341","https://openalex.org/W2495266147","https://openalex.org/W2780124704","https://openalex.org/W2922298118","https://openalex.org/W2945629925","https://openalex.org/W2949924544","https://openalex.org/W2962730651","https://openalex.org/W2962795401","https://openalex.org/W2967443589","https://openalex.org/W2981133004","https://openalex.org/W2981802563","https://openalex.org/W3036120140","https://openalex.org/W3083173864","https://openalex.org/W3099073275","https://openalex.org/W3102619627","https://openalex.org/W3105015787","https://openalex.org/W3107914916","https://openalex.org/W3125775899","https://openalex.org/W3208342928","https://openalex.org/W3209871427","https://openalex.org/W3211022607"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W4386815338","https://openalex.org/W2145836866","https://openalex.org/W2803255133"],"abstract_inverted_index":{"Automatic":[0],"control":[1],"of":[2,82,94,121,129],"conversational":[3,48],"agents":[4],"has":[5],"applications":[6],"from":[7],"animation,":[8],"through":[9],"human-computer":[10],"interaction,":[11],"to":[12,21,30,50,64,114],"robotics.":[13],"In":[14,33],"interactive":[15],"communication,":[16],"an":[17,69],"agent":[18],"must":[19],"move":[20],"express":[22],"its":[23],"own":[24],"discourse,":[25],"and":[26,56,72],"also":[27],"react":[28],"naturally":[29],"incoming":[31],"speech.":[32,100],"this":[34],"paper":[35],"we":[36],"propose":[37],"a":[38,61,74,119],"Flow":[39],"Variational":[40],"Autoencoder":[41],"(Flow-VAE)":[42],"deep":[43],"learning":[44],"architecture":[45],"for":[46,97],"transforming":[47],"speech":[49],"body":[51,109],"gesture,":[52],"during":[53],"both":[54],"speaking":[55],"listening.":[57],"The":[58],"model":[59,87],"uses":[60],"normalising":[62],"flow":[63],"perform":[65],"variational":[66,84],"inference":[67],"in":[68],"autoencoder":[70],"framework":[71],"is":[73,88,112],"more":[75],"expressive":[76,108],"distribution":[77],"than":[78],"the":[79,98,115,122,130],"Gaussian":[80],"approximation":[81],"conventional":[83],"autoencoders.":[85],"Our":[86,101],"non-deterministic,":[89],"so":[90],"can":[91],"produce":[92],"variations":[93],"plausible":[95],"gestures":[96],"same":[99],"evaluation":[102],"demonstrates":[103],"that":[104,111],"our":[105],"approach":[106],"produces":[107],"motion":[110],"close":[113],"ground":[116],"truth":[117],"using":[118],"fraction":[120],"trainable":[123],"parameters":[124],"compared":[125],"with":[126],"previous":[127],"state":[128],"art.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-26T08:31:28.666265","created_date":"2025-10-10T00:00:00"}