{"id":"https://openalex.org/W2888976508","doi":"https://doi.org/10.21437/interspeech.2018-2075","title":"Learning Interpretable Control Dimensions for Speech Synthesis by Using External Data","display_name":"Learning Interpretable Control Dimensions for Speech Synthesis by Using External Data","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2888976508","doi":"https://doi.org/10.21437/interspeech.2018-2075","mag":"2888976508"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-2075","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/f540e834-98df-4b96-bcfa-f7365d1c9028","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041839891","display_name":"Zack Hodari","orcid":null},"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":"Zack Hodari","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110238677","display_name":"Oliver Watts","orcid":null},"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":"Oliver Watts","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004616142","display_name":"Srikanth Ronanki","orcid":null},"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":"Srikanth Ronanki","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"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":["The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"32","last_page":"36"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7556936740875244},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.7096734642982483},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.6960678696632385},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.6328309774398804},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6071480512619019},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5971270799636841},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5448974370956421},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4479861557483673},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37453800439834595},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3405835032463074},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13046371936798096}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7556936740875244},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.7096734642982483},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.6960678696632385},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6328309774398804},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6071480512619019},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5971270799636841},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5448974370956421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4479861557483673},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37453800439834595},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3405835032463074},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13046371936798096},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2018-2075","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/f540e834-98df-4b96-bcfa-f7365d1c9028","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f540e834-98df-4b96-bcfa-f7365d1c9028","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":"Hodari, Z, Watts, O, Ronanki, S & King, S 2018, Learning interpretable control dimensions for speech synthesis by using external data. in Interspeech 2018. Hyderabad, India, pp. 32-36, Interspeech 2018, Hyderabad, India, 2/09/18. https://doi.org/10.21437/Interspeech.2018-2075","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/f540e834-98df-4b96-bcfa-f7365d1c9028","is_oa":false,"landing_page_url":"https://www.isca-speech.org/archive/Interspeech_2018/pdfs/2075.pdf","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/f540e834-98df-4b96-bcfa-f7365d1c9028","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f540e834-98df-4b96-bcfa-f7365d1c9028","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":"Hodari, Z, Watts, O, Ronanki, S & King, S 2018, Learning interpretable control dimensions for speech synthesis by using external data. in Interspeech 2018. Hyderabad, India, pp. 32-36, Interspeech 2018, Hyderabad, India, 2/09/18. https://doi.org/10.21437/Interspeech.2018-2075","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.44999998807907104,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G7898478334","display_name":null,"funder_award_id":"EP/P011586/1","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":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W163616957","https://openalex.org/W176245312","https://openalex.org/W1513862252","https://openalex.org/W1568716973","https://openalex.org/W1783473872","https://openalex.org/W1878590289","https://openalex.org/W2018338387","https://openalex.org/W2059721297","https://openalex.org/W2094147890","https://openalex.org/W2129703931","https://openalex.org/W2146334809","https://openalex.org/W2150769028","https://openalex.org/W2152205330","https://openalex.org/W2239141610","https://openalex.org/W2271840356","https://openalex.org/W2276408190","https://openalex.org/W2408520939","https://openalex.org/W2533262878","https://openalex.org/W2583643061","https://openalex.org/W2598638573","https://openalex.org/W2605320104","https://openalex.org/W2745595539","https://openalex.org/W2747664154","https://openalex.org/W2749891261","https://openalex.org/W2759925408","https://openalex.org/W2963130397","https://openalex.org/W4235154690","https://openalex.org/W4245744384"],"related_works":["https://openalex.org/W2317723112","https://openalex.org/W2475724061","https://openalex.org/W2773393136","https://openalex.org/W2174706483","https://openalex.org/W2997121352","https://openalex.org/W419536403","https://openalex.org/W2506280730","https://openalex.org/W4237969969","https://openalex.org/W1594297642","https://openalex.org/W2366328218"],"abstract_inverted_index":{"There":[0],"are":[1,47,57,97],"many":[2],"aspects":[3,27],"of":[4,25,28,36,94],"speech":[5],"that":[6,22,74,96],"we":[7,31],"might":[8],"want":[9],"to":[10,85,90,110,114],"control":[11,24,62,67,93,106],"when":[12],"creating":[13,65],"text-to-speech":[14],"(TTS)":[15],"systems.":[16],"We":[17,70,124],"present":[18],"a":[19,60,72,129],"general":[20],"method":[21,73,127],"enables":[23],"arbitrary":[26],"speech,":[29,118],"which":[30],"<br/>demonstrate":[32],"on":[33,51],"the":[34,81,87,92,101,108],"task":[35],"emotion":[37],"control.":[38],"Current":[39],"TTS":[40],"systems":[41],"use":[42],"supervised":[43],"machine":[44],"learning":[45],"and":[46],"therefore":[48],"heavily":[49],"reliant":[50],"labelled":[52,77,99],"data.":[53,103],"If":[54],"no":[55],"labels":[56],"available":[58],"for":[59,119],"desired":[61],"dimension,":[63],"then":[64],"interpretable":[66,105],"becomes":[68],"challenging.":[69],"introduce":[71],"uses":[75],"external,":[76],"data":[78,83],"(i.e.":[79],"not":[80,98],"original":[82,102],"used":[84],"train":[86],"acoustic":[88],"model)":[89],"enable":[91],"dimensions":[95],"in":[100],"Adding":[104],"allows":[107],"voice":[109],"be":[111],"manually":[112],"controlled":[113],"produce":[115],"more":[116],"engaging":[117],"applications":[120],"such":[121],"as":[122],"audiobooks.":[123],"evaluate":[125],"our":[126],"using":[128],"<br/>listening":[130],"test.":[131]},"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":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
