{"id":"https://openalex.org/W3195592874","doi":"https://doi.org/10.21437/ssw.2021-36","title":"Comparing acoustic and textual representations of previous linguistic context for improving Text-to-Speech","display_name":"Comparing acoustic and textual representations of previous linguistic context for improving Text-to-Speech","publication_year":2021,"publication_date":"2021-08-24","ids":{"openalex":"https://openalex.org/W3195592874","doi":"https://doi.org/10.21437/ssw.2021-36","mag":"3195592874"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2021-36","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2021-36","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"11th ISCA Speech Synthesis Workshop (SSW 11)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5033062208","display_name":"Pilar Oplustil-Gallegos","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":true,"raw_author_name":"Pilar Oplustil-Gallegos","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/A5072423792","display_name":"Johannah O\u2019Mahony","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":"Johannah O'Mahony","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":["https://openalex.org/A5033062208"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"205","last_page":"210"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.8981000185012817,"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/T12031","display_name":"Speech and dialogue systems","score":0.8981000185012817,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.8812000155448914,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.8323000073432922,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7440616488456726},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6227495074272156},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6006642580032349},{"id":"https://openalex.org/keywords/linguistic-context","display_name":"Linguistic context","score":0.5631043910980225},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.540908932685852},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4692554175853729},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4590027332305908},{"id":"https://openalex.org/keywords/linguistic-analysis","display_name":"Linguistic analysis","score":0.2424728274345398},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.1163785457611084}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7440616488456726},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6227495074272156},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6006642580032349},{"id":"https://openalex.org/C2993167945","wikidata":"https://www.wikidata.org/wiki/Q196626","display_name":"Linguistic context","level":3,"score":0.5631043910980225},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.540908932685852},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4692554175853729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4590027332305908},{"id":"https://openalex.org/C2987219923","wikidata":"https://www.wikidata.org/wiki/Q777864","display_name":"Linguistic analysis","level":2,"score":0.2424728274345398},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.1163785457611084},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/ssw.2021-36","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2021-36","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"11th ISCA Speech Synthesis Workshop (SSW 11)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/75a6c4cd-df70-4623-8dec-b699b139acf9","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/75a6c4cd-df70-4623-8dec-b699b139acf9","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":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W127438004","https://openalex.org/W2002875620","https://openalex.org/W2135360533","https://openalex.org/W2484713420","https://openalex.org/W2746419079","https://openalex.org/W2747252989","https://openalex.org/W2747874407","https://openalex.org/W2748592545","https://openalex.org/W2749434195","https://openalex.org/W2765860599","https://openalex.org/W2794490148","https://openalex.org/W2807717950","https://openalex.org/W2884225676","https://openalex.org/W2885800352","https://openalex.org/W2963300588","https://openalex.org/W2967220154","https://openalex.org/W2972375191","https://openalex.org/W2972906195","https://openalex.org/W2979826702","https://openalex.org/W2990883660","https://openalex.org/W3096634037","https://openalex.org/W3096643087","https://openalex.org/W3096791609","https://openalex.org/W3100400819","https://openalex.org/W3113076898","https://openalex.org/W3144667183","https://openalex.org/W3150572638","https://openalex.org/W3151309757","https://openalex.org/W3161113899","https://openalex.org/W3163339651","https://openalex.org/W3196231874","https://openalex.org/W3197324626"],"related_works":["https://openalex.org/W1973280724","https://openalex.org/W2562180202","https://openalex.org/W405926467","https://openalex.org/W2124840601","https://openalex.org/W2032228042","https://openalex.org/W2388873877","https://openalex.org/W2384413402","https://openalex.org/W2360049117","https://openalex.org/W2348415183","https://openalex.org/W2347577610"],"abstract_inverted_index":{"Text":[0],"alone":[1,117],"does":[2,126],"not":[3,127],"contain":[4],"sufficient":[5],"information":[6],"to":[7,36],"predict":[8],"the":[9,16,69,100,140],"spoken":[10],"form.Using":[11],"additional":[12],"information,":[13],"such":[14,49],"as":[15,50],"linguistic":[17,59],"context,":[18],"should":[19],"improve":[20],"Text-to-Speech":[21,64],"naturalness":[22,121],"in":[23,27],"general,":[24],"and":[25,95],"prosody":[26],"particular.Most":[28],"recent":[29],"research":[30],"on":[31,66],"using":[32,37],"context":[33,60,98,116],"is":[34],"limited":[35],"textual":[38,80,137],"features":[39,67,83,90],"of":[40,58,68,111],"adjacent":[41],"utterances,":[42],"extracted":[43,84],"with":[44,73,85,134],"large":[45,86],"pre-trained":[46,87],"language":[47],"models":[48,88],"BERT.In":[51],"this":[52],"paper,":[53],"we":[54],"compare":[55],"multiple":[56],"representations":[57,110],"by":[61],"conditioning":[62],"a":[63,123,135],"model":[65],"preceding":[70],"utterance.We":[71],"experiment":[72],"three":[74],"design":[75],"choices:":[76],"(1)":[77],"acoustic":[78,115,132],"vs.":[79,89,103],"representations;":[81],"(2)":[82],"learnt":[91],"jointly":[92],"during":[93],"training;":[94],"(3)":[96],"representing":[97],"at":[99],"utterance":[101],"level":[102],"word":[104],"level.Our":[105],"results":[106,142],"show":[107],"that":[108,125],"appropriate":[109],"either":[112],"text":[113],"or":[114],"yield":[118],"significantly":[119],"better":[120],"than":[122],"baseline":[124],"use":[128],"context.Combining":[129],"an":[130],"utterance-level":[131],"representation":[133,138],"word-level":[136],"gave":[139],"best":[141],"overall.":[143]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}