{"id":"https://openalex.org/W2747308422","doi":"https://doi.org/10.21437/interspeech.2017-894","title":"Predicting Head Pose from Speech with a Conditional Variational Autoencoder","display_name":"Predicting Head Pose from Speech with a Conditional Variational Autoencoder","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2747308422","doi":"https://doi.org/10.21437/interspeech.2017-894","mag":"2747308422"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-894","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-894","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ueaeprints.uea.ac.uk/id/eprint/64846/1/greenwood_Interspeech.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"raw_author_name":"David Greenwood","raw_affiliation_strings":["School of Computing Sciences University of East Anglia United Kingdom"],"affiliations":[{"raw_affiliation_string":"School of Computing Sciences University of East Anglia United Kingdom","institution_ids":["https://openalex.org/I1118541"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085340045","display_name":"Stephen D. Laycock","orcid":"https://orcid.org/0000-0002-7724-1369"},"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":"Stephen Laycock","raw_affiliation_strings":["School of Computing Sciences University of East Anglia United Kingdom"],"affiliations":[{"raw_affiliation_string":"School of Computing Sciences University of East Anglia United Kingdom","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/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":"Iain Matthews","raw_affiliation_strings":["School of Computing Sciences University of East Anglia United Kingdom"],"affiliations":[{"raw_affiliation_string":"School of Computing Sciences University of East Anglia United Kingdom","institution_ids":["https://openalex.org/I1118541"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016362960"],"corresponding_institution_ids":["https://openalex.org/I1118541"],"apc_list":null,"apc_paid":null,"fwci":3.0578,"has_fulltext":true,"cited_by_count":47,"citation_normalized_percentile":{"value":0.91683887,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3991","last_page":"3995"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9991999864578247,"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/T11448","display_name":"Face recognition and analysis","score":0.9973000288009644,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9961000084877014,"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/computer-science","display_name":"Computer science","score":0.8256586790084839},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7695302963256836},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.6477081179618835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6149092316627502},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6052365899085999},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5784400105476379},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5708087086677551},{"id":"https://openalex.org/keywords/emotive","display_name":"Emotive","score":0.45978879928588867},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4578292965888977},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4511867165565491},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4010757803916931},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37730738520622253},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3269290030002594},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2382928729057312}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8256586790084839},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7695302963256836},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.6477081179618835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6149092316627502},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6052365899085999},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5784400105476379},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5708087086677551},{"id":"https://openalex.org/C2776215170","wikidata":"https://www.wikidata.org/wiki/Q5373820","display_name":"Emotive","level":2,"score":0.45978879928588867},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4578292965888977},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4511867165565491},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4010757803916931},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37730738520622253},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3269290030002594},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2382928729057312},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2017-894","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-894","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:ueaeprints.uea.ac.uk:64846","is_oa":true,"landing_page_url":null,"pdf_url":"https://ueaeprints.uea.ac.uk/id/eprint/64846/1/greenwood_Interspeech.pdf","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":{"id":"pmh:oai:ueaeprints.uea.ac.uk:64846","is_oa":true,"landing_page_url":null,"pdf_url":"https://ueaeprints.uea.ac.uk/id/eprint/64846/1/greenwood_Interspeech.pdf","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"},"sustainable_development_goals":[{"score":0.5,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2747308422.pdf","grobid_xml":"https://content.openalex.org/works/W2747308422.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1483472084","https://openalex.org/W1496997718","https://openalex.org/W1555696814","https://openalex.org/W1810943226","https://openalex.org/W1909320841","https://openalex.org/W1970088388","https://openalex.org/W1974604838","https://openalex.org/W1984541135","https://openalex.org/W1999681822","https://openalex.org/W2020661758","https://openalex.org/W2021992838","https://openalex.org/W2032618685","https://openalex.org/W2053831280","https://openalex.org/W2082308025","https://openalex.org/W2091432990","https://openalex.org/W2108501770","https://openalex.org/W2118163921","https://openalex.org/W2124399597","https://openalex.org/W2126398289","https://openalex.org/W2130942839","https://openalex.org/W2142487393","https://openalex.org/W2403714865","https://openalex.org/W2436270489","https://openalex.org/W2470142083","https://openalex.org/W2949416428","https://openalex.org/W2963223306","https://openalex.org/W4252434905","https://openalex.org/W4299390018"],"related_works":["https://openalex.org/W3004257401","https://openalex.org/W4394785709","https://openalex.org/W4309969736","https://openalex.org/W2770818364","https://openalex.org/W2953501176","https://openalex.org/W2965095304","https://openalex.org/W2470043383","https://openalex.org/W3034474024","https://openalex.org/W4317242571","https://openalex.org/W2786460063"],"abstract_inverted_index":{"Natural":[0],"movement":[1],"plays":[2],"a":[3,46,51,159,169,186],"significant":[4],"role":[5],"in":[6,99,133],"realistic":[7],"speech":[8,55,85,117,140,187],"animation.":[9],"Numerous":[10],"studies":[11],"have":[12,65,110],"demonstrated":[13],"the":[14,20,54,59,137,177,180],"contribution":[15],"visual":[16,35],"cues":[17],"make":[18],"to":[19,49,57,76,94,135,182,188],"degree":[21],"we,":[22],"as":[23],"human":[24],"observers,":[25],"find":[26],"an":[27,112],"animation":[28],"acceptable.":[29],"Rigid":[30],"head":[31,60,101,144,161,189],"motion":[32,87,162],"is":[33,45,69],"one":[34,181],"mode":[36,56],"that":[37,67,89,139,185],"universally":[38],"co-occurs":[39],"with":[40,96,142,153],"speech,":[41],"and":[42,83,118],"so":[43],"it":[44],"reasonable":[47],"strategy":[48],"seek":[50],"transformation":[52],"from":[53],"predict":[58,95],"pose.":[61,102],"Several":[62],"previous":[63],"authors":[64],"shown":[66],"prediction":[68],"possible,":[70],"but":[71],"experiments":[72],"are":[73,90],"typically":[74],"confined":[75],"rigidly":[77],"produced":[78],"dialogue.":[79],"Natural,":[80],"expressive,":[81],"emotive":[82],"prosodic":[84],"exhibit":[86],"patterns":[88],"far":[91],"more":[92],"difficult":[93],"considerable":[97],"variation":[98],"expected":[100],"Recently,":[103],"Long":[104],"Short":[105],"Term":[106],"Memory":[107],"(LSTM)":[108],"networks":[109],"become":[111],"important":[113],"tool":[114],"for":[115],"modelling":[116],"natural":[119],"language":[120],"tasks.":[121],"We":[122,146],"employ":[123],"Deep":[124],"Bi-Directional":[125],"LSTMs":[126],"(BLSTM)":[127],"capable":[128],"of":[129,179],"learning":[130],"long-term":[131],"structure":[132],"language,":[134],"model":[136,150,191],"relationship":[138],"has":[141],"rigid":[143],"motion.":[145,155],"then":[147],"extend":[148],"our":[149],"by":[151],"conditioning":[152],"prior":[154],"Finally,":[156],"we":[157],"introduce":[158],"generative":[160],"model,":[163],"conditioned":[164],"on":[165],"audio":[166],"features":[167],"using":[168],"Conditional":[170],"Variational":[171],"Autoencoder":[172],"(CVAE).":[173],"Each":[174],"approach":[175],"mitigates":[176],"problems":[178],"many":[183],"mapping":[184],"pose":[190],"must":[192],"accommodate":[193]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4}],"updated_date":"2026-04-19T08:26:33.389920","created_date":"2025-10-10T00:00:00"}