{"id":"https://openalex.org/W1783473872","doi":"https://doi.org/10.21437/interspeech.2015-128","title":"Sentence-level control vectors for deep neural network speech synthesis","display_name":"Sentence-level control vectors for deep neural network speech synthesis","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W1783473872","doi":"https://doi.org/10.21437/interspeech.2015-128","mag":"1783473872"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-128","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.pure.ed.ac.uk/ws/files/20017624/master.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110238677","display_name":"Oliver Watts","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oliver Watts","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102765381","display_name":"Zhizheng Wu","orcid":"https://orcid.org/0009-0001-1192-9857"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhizheng Wu","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":["School of Philosophy Psychology and Language Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Philosophy Psychology and Language Sciences","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":45,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2217","last_page":"2221"},"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/T10028","display_name":"Topic Modeling","score":0.9984999895095825,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9973999857902527,"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":0.7056628465652466},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5770969390869141},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5421676635742188},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5218492746353149},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4963720440864563},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4886968433856964},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48818427324295044},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4523783326148987}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7056628465652466},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5770969390869141},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5421676635742188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5218492746353149},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4963720440864563},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4886968433856964},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48818427324295044},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4523783326148987}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2015-128","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/d4a168ce-650e-40c5-8dd6-ed5d366d6df3","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/d4a168ce-650e-40c5-8dd6-ed5d366d6df3","pdf_url":"https://www.pure.ed.ac.uk/ws/files/20017624/master.pdf","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/d4a168ce-650e-40c5-8dd6-ed5d366d6df3","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/d4a168ce-650e-40c5-8dd6-ed5d366d6df3","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":"Watts, O, Wu, Z & King, S 2015, Sentence-level control vectors for deep neural network speech synthesis. in INTERSPEECH 2015 16th Annual Conference of the International Speech Communication Association. International Speech Communication Association, pp. 2217-2221. < http://www.isca-speech.org/archive/interspeech_2015/i15_2217.html >","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/d4a168ce-650e-40c5-8dd6-ed5d366d6df3","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/d4a168ce-650e-40c5-8dd6-ed5d366d6df3","pdf_url":"https://www.pure.ed.ac.uk/ws/files/20017624/master.pdf","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":[{"id":"https://metadata.un.org/sdg/4","score":0.699999988079071,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4055593462","display_name":null,"funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1783473872.pdf","grobid_xml":"https://content.openalex.org/works/W1783473872.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W80543058","https://openalex.org/W141956881","https://openalex.org/W1499332833","https://openalex.org/W1854240507","https://openalex.org/W1970689298","https://openalex.org/W1971670143","https://openalex.org/W1977362129","https://openalex.org/W1993409002","https://openalex.org/W1996430422","https://openalex.org/W2015687745","https://openalex.org/W2039800941","https://openalex.org/W2042600255","https://openalex.org/W2074854222","https://openalex.org/W2090755665","https://openalex.org/W2102003408","https://openalex.org/W2112021726","https://openalex.org/W2116082100","https://openalex.org/W2123442489","https://openalex.org/W2134973740","https://openalex.org/W2145247325","https://openalex.org/W2154920538","https://openalex.org/W2156692643","https://openalex.org/W2296111744","https://openalex.org/W2396043161","https://openalex.org/W2998704965","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2375873920","https://openalex.org/W2146114872","https://openalex.org/W2392060890","https://openalex.org/W2392760275","https://openalex.org/W2083530853","https://openalex.org/W2982905616","https://openalex.org/W2393172683","https://openalex.org/W2009831055","https://openalex.org/W2368686738","https://openalex.org/W2389383932"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,15,34,47,50,58,92,100,112,120,128,135,142,179],"use":[4],"of":[5,10,17,46,78,111,146],"a":[6,18,26,55,70,75],"low-dimensional":[7],"vector":[8],"representation":[9,77],"sentence":[11,90,114],"acoustics":[12],"to":[13,122,172],"control":[14,165],"output":[16],"feed-forward":[19],"deep":[20],"neural":[21],"network":[22,40,51,102,121],"text-to-speech":[23],"system":[24],"on":[25,54,108],"sentence-by-sentence":[27],"basis.":[28],"Vector":[29],"representations":[30],"for":[31,88,124],"sentences":[32],"in":[33,91,127,178],"training":[35,41,93,180],"corpus":[36],"are":[37,65,96,106,168],"learned":[38,76],"during":[39],"along":[42],"with":[43,99,163,175],"other":[44],"parameters":[45,87,105,117],"model.":[48],"Although":[49],"is":[52,131],"trained":[53],"frame-by-frame":[56],"basis,":[57],"standard":[59,101,136],"frame-level":[60],"inputs":[61],"representing":[62],"linguistic":[63,137,161],"features":[64,68,162],"supplemented":[66],"by":[67,158],"from":[69,134],"projection":[71,83],"layer":[72,84],"which":[73,95,130,167],"outputs":[74],"sentence-level":[79,125,164],"acoustic":[80],"characteristics.":[81],"The":[82],"contains":[85],"dedicated":[86],"each":[89],"data":[94,129],"optimised":[97,107],"jointly":[98],"weights.":[103],"Sentence-specific":[104],"all":[109],"frames":[110],"relevant":[113],"--":[115],"these":[116],"therefore":[118],"allow":[119],"account":[123],"variation":[126],"not":[132],"predictable":[133],"inputs.":[138],"Results":[139],"show":[140],"that":[141],"global":[143],"prosodic":[144],"characteristics":[145],"synthetic":[147],"speech":[148],"can":[149],"be":[150,173],"controlled":[151],"simply":[152],"and":[153],"robustly":[154],"at":[155],"run":[156],"time":[157],"supplementing":[159],"basic":[160],"vectors":[166],"novel":[169],"but":[170],"designed":[171],"consistent":[174],"those":[176],"observed":[177],"corpus.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":11}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}