{"id":"https://openalex.org/W2721682741","doi":"https://doi.org/10.1109/icassp.2017.7953092","title":"Expressive visual text to speech and expression adaptation using deep neural networks","display_name":"Expressive visual text to speech and expression adaptation using deep neural networks","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2721682741","doi":"https://doi.org/10.1109/icassp.2017.7953092","mag":"2721682741"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.17863/cam.28066","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003499948","display_name":"Jonathan Parker","orcid":"https://orcid.org/0000-0001-7563-1630"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jonathan Parker","raw_affiliation_strings":["Department of Engineering, University of Cambridge, UK","Toshiba Research Europe Limited, Cambridge Research Laboratorv, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Toshiba Research Europe Limited, Cambridge Research Laboratorv, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110289715","display_name":"Ranniery Maia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ranniery Maia","raw_affiliation_strings":["Toshiba Research Europe Limited, Cambridge Research Laboratorv, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Limited, Cambridge Research Laboratorv, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035745788","display_name":"Yannis Stylianou","orcid":null},"institutions":[{"id":"https://openalex.org/I142617266","display_name":"University of Crete","ror":"https://ror.org/00dr28g20","country_code":"GR","type":"education","lineage":["https://openalex.org/I142617266"]},{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB","GR"],"is_corresponding":false,"raw_author_name":"Yannis Stylianou","raw_affiliation_strings":["Department of Computer Science, University of Crete, Greece","Toshiba Research Europe Limited, Cambridge Research Laboratorv, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Crete, Greece","institution_ids":["https://openalex.org/I142617266"]},{"raw_affiliation_string":"Toshiba Research Europe Limited, Cambridge Research Laboratorv, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018207993","display_name":"Roberto Cipolla","orcid":"https://orcid.org/0000-0002-8999-2151"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Roberto Cipolla","raw_affiliation_strings":["Department of Engineering, University of Cambridge, UK","Toshiba Research Europe Limited, Cambridge Research Laboratorv, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Toshiba Research Europe Limited, Cambridge Research Laboratorv, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.739,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.80574324,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"5","issue":null,"first_page":"4920","last_page":"4924"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9987000226974487,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9984999895095825,"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/speech-recognition","display_name":"Speech recognition","score":0.7473552823066711},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.715620219707489},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6479874849319458},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.627578616142273},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.6046547293663025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5559334754943848},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5538427829742432},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44412821531295776},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4403054416179657},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.4388507306575775},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.41235268115997314},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3914411664009094}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7473552823066711},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.715620219707489},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6479874849319458},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.627578616142273},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.6046547293663025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5559334754943848},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5538427829742432},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44412821531295776},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4403054416179657},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4388507306575775},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.41235268115997314},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3914411664009094},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2017.7953092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:generic.eprints.org:922296","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/922296/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/280701","is_oa":false,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/280701","pdf_url":null,"source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"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":"Conference Object"},{"id":"doi:10.17863/cam.28066","is_oa":true,"landing_page_url":"https://doi.org/10.17863/cam.28066","pdf_url":null,"source":{"id":"https://openalex.org/S7407050737","display_name":"Apollo","issn_l":null,"issn":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.17863/cam.28066","is_oa":true,"landing_page_url":"https://doi.org/10.17863/cam.28066","pdf_url":null,"source":{"id":"https://openalex.org/S7407050737","display_name":"Apollo","issn_l":null,"issn":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6100000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1569907127","https://openalex.org/W1779294284","https://openalex.org/W2025638820","https://openalex.org/W2045158511","https://openalex.org/W2062227835","https://openalex.org/W2102003408","https://openalex.org/W2104480821","https://openalex.org/W2107813907","https://openalex.org/W2115402659","https://openalex.org/W2121402967","https://openalex.org/W2129360799","https://openalex.org/W2131744502","https://openalex.org/W2152826865","https://openalex.org/W2154920538","https://openalex.org/W2172803778","https://openalex.org/W2194775991","https://openalex.org/W2289286917","https://openalex.org/W2397059489","https://openalex.org/W2605320104","https://openalex.org/W6675380101","https://openalex.org/W6679775712","https://openalex.org/W6682634897"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2097963413","https://openalex.org/W2294335174","https://openalex.org/W2025614924","https://openalex.org/W3145575561","https://openalex.org/W2001275470","https://openalex.org/W2073996508","https://openalex.org/W1591475660","https://openalex.org/W3000197790"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,71],"present":[4,72],"an":[5,21],"expressive":[6],"visual":[7],"text":[8,23],"to":[9,35,81],"speech":[10],"system":[11],"(VTTS)":[12],"based":[13,110],"on":[14],"a":[15,26,62,73,77,83,87],"deep":[16],"neural":[17],"network":[18],"(DNN).":[19],"Given":[20],"input":[22],"sentence":[24],"and":[25],"set":[27],"of":[28,54,64,75,90],"expression":[29,85],"tags,":[30],"the":[31,39,44,55,58,67,96,105],"VTTS":[32,99,111],"is":[33,100],"able":[34],"produce":[36],"not":[37],"only":[38],"audio":[40],"speech,":[41],"but":[42],"also":[43],"accompanying":[45],"facial":[46],"movements.":[47],"The":[48],"expressions":[49,56,65],"can":[50],"either":[51],"be":[52],"one":[53],"in":[57],"training":[59,68,91],"corpus":[60],"or":[61],"blend":[63],"from":[66],"corpus.":[69],"Furthermore,":[70],"method":[74],"adapting":[76],"previously":[78],"trained":[79],"DNN":[80],"include":[82],"new":[84],"using":[86],"small":[88],"amount":[89],"data.":[92],"Experiments":[93],"show":[94],"that":[95],"proposed":[97],"DNN-based":[98],"preferred":[101],"by":[102],"57.9%":[103],"over":[104],"baseline":[106],"hidden":[107],"Markov":[108],"model":[109],"which":[112],"uses":[113],"cluster":[114],"adaptive":[115],"training.":[116]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}