{"id":"https://openalex.org/W2745595539","doi":"https://doi.org/10.21437/interspeech.2017-171","title":"Principles for Learning Controllable TTS from Annotated and Latent Variation","display_name":"Principles for Learning Controllable TTS from Annotated and Latent Variation","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2745595539","doi":"https://doi.org/10.21437/interspeech.2017-171","mag":"2745595539"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-171","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-171","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/7a2e61f2-fc0a-4db2-a257-217bef857261","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091432739","display_name":"Gustav Eje Henter","orcid":"https://orcid.org/0000-0002-1643-1054"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Gustav Eje Henter","raw_affiliation_strings":["Digital Content and Media Sciences Research Division, National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Content and Media Sciences Research Division, National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019530089","display_name":"Jaime Lorenzo-Trueba","orcid":"https://orcid.org/0000-0003-0459-1429"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jaime Lorenzo-Trueba","raw_affiliation_strings":["Digital Content and Media Sciences Research Division, National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Content and Media Sciences Research Division, National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327839","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0001-8246-0606"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["Digital Content and Media Sciences Research Division, National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Content and Media Sciences Research Division, National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["The Centre for Speech Technology Research, the University of Edinburgh, UK","Digital Content and Media Sciences Research Division, National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, the University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Digital Content and Media Sciences Research Division, National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3956","last_page":"3960"},"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":0.9980999827384949,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9972000122070312,"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/computer-science","display_name":"Computer science","score":0.7343711256980896},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.6785988807678223},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.6759104132652283},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.645614504814148},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.577652633190155},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5670813322067261},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5647282600402832},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5417147278785706},{"id":"https://openalex.org/keywords/linear-subspace","display_name":"Linear subspace","score":0.5065180063247681},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49580320715904236},{"id":"https://openalex.org/keywords/latent-variable-model","display_name":"Latent variable model","score":0.4583747386932373},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4381190538406372},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.41428664326667786},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32857006788253784},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10768046975135803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7343711256980896},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.6785988807678223},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6759104132652283},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.645614504814148},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.577652633190155},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5670813322067261},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5647282600402832},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5417147278785706},{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.5065180063247681},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49580320715904236},{"id":"https://openalex.org/C65965080","wikidata":"https://www.wikidata.org/wiki/Q1806885","display_name":"Latent variable model","level":3,"score":0.4583747386932373},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4381190538406372},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.41428664326667786},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32857006788253784},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10768046975135803},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2017-171","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-171","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:pure.ed.ac.uk:publications/7a2e61f2-fc0a-4db2-a257-217bef857261","is_oa":true,"landing_page_url":"http://www.isca-speech.org/archive/Interspeech_2017/pdfs/0171.PDF","pdf_url":"https://www.research.ed.ac.uk/en/publications/7a2e61f2-fc0a-4db2-a257-217bef857261","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":""},{"id":"pmh:oai:pure.ed.ac.uk:openaire/7a2e61f2-fc0a-4db2-a257-217bef857261","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/7a2e61f2-fc0a-4db2-a257-217bef857261","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"Henter, G, Lorenzo-Trueba, J, Wang, X & Yamagishi, J 2017, Principles for learning controllable TTS from annotated and latent variation. in Proceedings Interspeech 2017. Interspeech, International Speech Communication Association, pp. 3956-3960, Interspeech 2017, Stockholm, Sweden, 20/08/17. https://doi.org/10.21437/Interspeech.2017-171","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/7a2e61f2-fc0a-4db2-a257-217bef857261","is_oa":true,"landing_page_url":"http://www.isca-speech.org/archive/Interspeech_2017/pdfs/0171.PDF","pdf_url":"https://www.research.ed.ac.uk/en/publications/7a2e61f2-fc0a-4db2-a257-217bef857261","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":""},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2745595539.pdf","grobid_xml":"https://content.openalex.org/works/W2745595539.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W304834817","https://openalex.org/W1492383498","https://openalex.org/W1493898446","https://openalex.org/W1570874634","https://openalex.org/W1783473872","https://openalex.org/W1959608418","https://openalex.org/W2039800941","https://openalex.org/W2049633694","https://openalex.org/W2064675550","https://openalex.org/W2098372067","https://openalex.org/W2112021726","https://openalex.org/W2116082100","https://openalex.org/W2119929864","https://openalex.org/W2121044470","https://openalex.org/W2125838338","https://openalex.org/W2129142580","https://openalex.org/W2154920538","https://openalex.org/W2188827208","https://openalex.org/W2338186431","https://openalex.org/W2400063444","https://openalex.org/W2471520273","https://openalex.org/W2516321201","https://openalex.org/W2519091744","https://openalex.org/W2605320104","https://openalex.org/W2750515423","https://openalex.org/W2759925408","https://openalex.org/W4235154690","https://openalex.org/W4253573210"],"related_works":["https://openalex.org/W2461917396","https://openalex.org/W2037497866","https://openalex.org/W4243467573","https://openalex.org/W1502435251","https://openalex.org/W62001224","https://openalex.org/W3032390039","https://openalex.org/W1584341211","https://openalex.org/W3122667150","https://openalex.org/W4393387622","https://openalex.org/W3145681568"],"abstract_inverted_index":{"For":[0],"building":[1],"flexible":[2],"and":[3,16,79],"appealing":[4],"high-quality":[5],"speech":[6,156,173],"synthesisers,":[7],"it":[8],"is":[9],"desirable":[10],"to":[11,14,42,116,126,148,190],"be":[12,59,73],"able":[13],"accommodate":[15],"reproduce":[17],"fine":[18],"variations":[19],"in":[20,24,40,49,82,135,151,177],"vocal":[21],"expression":[22,153,178],"present":[23,131],"natural":[25],"speech.":[26,138],"Synthesisers":[27],"can":[28,58,72,171],"enable":[29],"control":[30,38,56,98],"over":[31],"such":[32,95],"output":[33],"properties":[34],"by":[35,111],"adding":[36],"<br/>adjustable":[37],"parameters":[39],"parallel":[41],"their":[43],"text":[44],"input.":[45],"If":[46],"not":[47],"annotated":[48,137,158],"training":[50],"data,":[51],"the":[52,63,109,113,184],"values":[53],"of":[54,91,129,186],"these":[55],"inputs":[57,94],"optimised":[60],"jointly":[61],"with":[62,159,174],"model":[64],"parameters.":[65],"We":[66,106],"describe":[67],"how":[68],"this":[69],"established":[70],"method":[71,110],"seen":[74],"as":[75,96],"approximate":[76],"maximum":[77],"likelihood":[78],"MAP":[80],"inference":[81],"a":[83,101,120,155],"latent":[84,114],"variable":[85],"model.":[86],"This":[87,123],"puts":[88],"previous":[89],"ideas":[90],"(learned)":[92],"synthesiser":[93],"sentence-level":[97],"vectors":[99],"on":[100],"more":[102],"solid":[103],"theoretical":[104],"footing.":[105],"furthermore":[107],"extend":[108],"restricting":[112],"variables":[115],"orthogonal":[117],"subspaces":[118],"via":[119],"sparse":[121],"prior.":[122],"enables":[124],"us":[125],"learn":[127,149],"dimensions":[128],"variation":[130],"also":[132],"within":[133,179],"classes":[134],"coarsely":[136],"As":[139],"an":[140,144,191],"example,":[141],"we":[142],"train":[143],"LSTM-based":[145],"TTS":[146],"system":[147,193],"nuances":[150],"emotional":[152],"from":[154],"database":[157],"seven":[160],"different":[161],"acted":[162],"emotions.":[163],"Listening":[164],"tests":[165],"show":[166],"that":[167],"our":[168],"proposal":[169],"successfully":[170],"synthesise":[172],"discernible":[175],"differences":[176],"each":[180],"emotion,":[181],"without":[182,194],"compromising":[183],"recognisability":[185],"synthesised":[187],"emotions":[188],"compared":[189],"identical":[192],"learned":[195],"nuances.":[196]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}