{"id":"https://openalex.org/W2059721297","doi":"https://doi.org/10.1109/jstsp.2013.2294938","title":"Integrated Expression Prediction and Speech Synthesis From Text","display_name":"Integrated Expression Prediction and Speech Synthesis From Text","publication_year":2014,"publication_date":"2014-01-31","ids":{"openalex":"https://openalex.org/W2059721297","doi":"https://doi.org/10.1109/jstsp.2013.2294938","mag":"2059721297"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2013.2294938","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2013.2294938","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-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/A5070433127","display_name":"Langzhou Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]},{"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","JP"],"is_corresponding":true,"raw_author_name":"Langzhou Chen","raw_affiliation_strings":["Speech Technology Group, Cambridge Research Laboratory, Toshiba Research Europe Limited, Cambridge, United Kingdom","Toshiba Res. Eur., Ltd., Cambridge, UK#TAB#"],"affiliations":[{"raw_affiliation_string":"Speech Technology Group, Cambridge Research Laboratory, Toshiba Research Europe Limited, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210143477"]},{"raw_affiliation_string":"Toshiba Res. Eur., Ltd., Cambridge, UK#TAB#","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050766679","display_name":"Mark Gales","orcid":"https://orcid.org/0000-0002-5311-8219"},"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/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Mark J. F. Gales","raw_affiliation_strings":["Machine Intelligence Laboratory, Department of Engineering, University of Cambridge, Cambridge, United Kingdom","Toshiba Res. Eur., Ltd., Cambridge, UK#TAB#"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Laboratory, Department of Engineering, University of Cambridge, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Toshiba Res. Eur., Ltd., Cambridge, UK#TAB#","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075928867","display_name":"Norbert Braunschweiler","orcid":"https://orcid.org/0000-0003-1388-440X"},"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"]},{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Norbert Braunschweiler","raw_affiliation_strings":["Speech Technology Group, Cambridge Research Laboratory, Toshiba Research Europe Limited, Cambridge, United Kingdom","Toshiba Res. Eur., Ltd., Cambridge, UK#TAB#"],"affiliations":[{"raw_affiliation_string":"Speech Technology Group, Cambridge Research Laboratory, Toshiba Research Europe Limited, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210143477"]},{"raw_affiliation_string":"Toshiba Res. Eur., Ltd., Cambridge, UK#TAB#","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112250968","display_name":"Masami Akamine","orcid":null},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masami Akamine","raw_affiliation_strings":["Corporate Research and Development Center, Toshiba Corporation, Kawasaki, Japan","Corp. R&D Center, Toshiba Corp., Kawasaki, Japan"],"affiliations":[{"raw_affiliation_string":"Corporate Research and Development Center, Toshiba Corporation, Kawasaki, Japan","institution_ids":["https://openalex.org/I1292669757"]},{"raw_affiliation_string":"Corp. R&D Center, Toshiba Corp., Kawasaki, Japan","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111076409","display_name":"Kate Knill","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"]},{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Kate Knill","raw_affiliation_strings":["Toshiba Research Europe Limited, Cambridge, U.K","Toshiba Res. Eur., Ltd., Cambridge, UK#TAB#"],"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Limited, Cambridge, U.K","institution_ids":["https://openalex.org/I4210143477"]},{"raw_affiliation_string":"Toshiba Res. Eur., Ltd., Cambridge, UK#TAB#","institution_ids":["https://openalex.org/I1292669757"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5070433127"],"corresponding_institution_ids":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"],"apc_list":null,"apc_paid":null,"fwci":2.5371,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.91084662,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"8","issue":"2","first_page":"323","last_page":"335"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9970999956130981,"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/speech-synthesis","display_name":"Speech synthesis","score":0.8005312085151672},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7833967804908752},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.6527247428894043},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6071851253509521},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5988568663597107},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46980175375938416},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4261709451675415},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3997899293899536},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08858427405357361}],"concepts":[{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.8005312085151672},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7833967804908752},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.6527247428894043},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6071851253509521},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5988568663597107},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46980175375938416},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4261709451675415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3997899293899536},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08858427405357361},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jstsp.2013.2294938","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2013.2294938","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:generic.eprints.org:632502","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/632502/","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":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2533495","https://openalex.org/W51255321","https://openalex.org/W80543058","https://openalex.org/W170974841","https://openalex.org/W1517939602","https://openalex.org/W1523817494","https://openalex.org/W1989664640","https://openalex.org/W2002342963","https://openalex.org/W2009417200","https://openalex.org/W2025638820","https://openalex.org/W2069631319","https://openalex.org/W2079521622","https://openalex.org/W2085013480","https://openalex.org/W2087110403","https://openalex.org/W2091430793","https://openalex.org/W2102146461","https://openalex.org/W2105468141","https://openalex.org/W2118714763","https://openalex.org/W2125552374","https://openalex.org/W2129142580","https://openalex.org/W2150791533","https://openalex.org/W2153914468","https://openalex.org/W2156146072","https://openalex.org/W2156450495","https://openalex.org/W2159290663","https://openalex.org/W2168980558","https://openalex.org/W2171002058","https://openalex.org/W2269105564","https://openalex.org/W2283817422","https://openalex.org/W2292984643","https://openalex.org/W2294232014","https://openalex.org/W2400658454","https://openalex.org/W2404480901","https://openalex.org/W2406483023","https://openalex.org/W6600088033","https://openalex.org/W6603264027","https://openalex.org/W6712828593","https://openalex.org/W6713463683","https://openalex.org/W6713894373"],"related_works":["https://openalex.org/W2062195135","https://openalex.org/W2392243736","https://openalex.org/W86652014","https://openalex.org/W3129895999","https://openalex.org/W2328518092","https://openalex.org/W3101249758","https://openalex.org/W2382079200","https://openalex.org/W2374091470","https://openalex.org/W4388218547","https://openalex.org/W127416991"],"abstract_inverted_index":{"Generating":[0,34],"expressive,":[1],"naturally":[2],"sounding,":[3],"speech":[4,9,36,53,116,129],"from":[5,37,48],"text":[6,38],"using":[7],"a":[8,14,55,103,132,151,157],"synthesis":[10,79,154],"(TTS)":[11],"system":[12],"is":[13,25,30,80],"highly":[15],"challenging":[16],"problem.":[17],"However":[18],"for":[19,102],"tasks":[20],"such":[21],"as":[22],"audiobooks":[23],"it":[24],"essential":[26],"if":[27],"their":[28],"use":[29],"to":[31,90],"become":[32],"widespread.":[33],"expressive":[35,46,78,99,128,153],"can":[39],"be":[40],"divided":[41],"into":[42],"two":[43,84],"parts:":[44],"predicting":[45],"information":[47],"text;":[49],"and":[50,75,108,115,135],"synthesizing":[51],"the":[52,72,83,112,122,138,148],"with":[54],"particular":[56],"expression.":[57],"Traditionally":[58],"these":[59],"components":[60],"have":[61],"been":[62],"studied":[63],"separately.":[64],"This":[65],"paper":[66],"proposes":[67],"an":[68],"integrated":[69],"approach,":[70],"where":[71,137],"training":[73,110],"data":[74],"representation":[76,105],"of":[77,96,106,111,150],"shared":[81],"across":[82],"components.":[85],"There":[86],"are":[87],"several":[88],"advantages":[89],"this":[91],"scheme":[92],"including:":[93],"robust":[94],"handling":[95],"automatically":[97],"generated":[98],"labels;":[100],"support":[101],"continuous":[104,152],"expressions;":[107],"joint":[109],"expression":[113,139],"predictor":[114],"synthesizer.":[117],"Synthesis":[118],"experiments":[119],"indicated":[120],"that":[121],"proposed":[123],"approach":[124],"produced":[125],"far":[126],"more":[127],"than":[130],"both":[131],"neutral":[133],"TTS":[134],"one":[136],"was":[140],"randomly":[141],"selected.":[142],"The":[143],"experimental":[144],"results":[145],"also":[146],"show":[147],"advantage":[149],"space":[155],"over":[156],"discrete":[158],"space.":[159]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}