{"id":"https://openalex.org/W4296068977","doi":"https://doi.org/10.21437/interspeech.2022-10167","title":"Combining conversational speech with read speech to improve prosody in Text-to-Speech synthesis","display_name":"Combining conversational speech with read speech to improve prosody in Text-to-Speech synthesis","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296068977","doi":"https://doi.org/10.21437/interspeech.2022-10167"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10167","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10167","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/61c6adc1-ed48-4c64-9f5d-924521ddf2dc","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Johannah O'Mahony","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011726172","display_name":"Catherine Lai","orcid":"https://orcid.org/0000-0001-8861-0281"},"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":"Catherine Lai","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","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, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5072423792"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3388","last_page":"3392"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9993000030517578,"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":0.9983999729156494,"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/prosody","display_name":"Prosody","score":0.8292734026908875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7826240062713623},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.712944507598877},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6675407886505127},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.6159671545028687},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4911298453807831},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4910862445831299},{"id":"https://openalex.org/keywords/chinese-speech-synthesis","display_name":"Chinese speech synthesis","score":0.4479826092720032},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.42567938566207886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3584686517715454},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15569964051246643},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.10508626699447632}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8292734026908875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7826240062713623},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.712944507598877},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6675407886505127},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6159671545028687},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4911298453807831},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4910862445831299},{"id":"https://openalex.org/C73411735","wikidata":"https://www.wikidata.org/wiki/Q16369","display_name":"Chinese speech synthesis","level":4,"score":0.4479826092720032},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.42567938566207886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3584686517715454},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15569964051246643},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.10508626699447632},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2022-10167","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10167","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/61c6adc1-ed48-4c64-9f5d-924521ddf2dc","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/61c6adc1-ed48-4c64-9f5d-924521ddf2dc","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":"O'Mahony, J, Lai, C & King, S 2022, Combining conversational speech with read speech to improve prosody in Text-to-Speech synthesis. in H Ko & J H L Hansen (eds), Proceedings of Interspeech 2022. Interspeech - Annual Conference of the International Speech Communication Association, pp. 3388-3392. https://doi.org/10.21437/Interspeech.2022-10167","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/61c6adc1-ed48-4c64-9f5d-924521ddf2dc","is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.11820/61c6adc1-ed48-4c64-9f5d-924521ddf2dc","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/61c6adc1-ed48-4c64-9f5d-924521ddf2dc","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/61c6adc1-ed48-4c64-9f5d-924521ddf2dc","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":"O'Mahony, J, Lai, C & King, S 2022, Combining conversational speech with read speech to improve prosody in Text-to-Speech synthesis. in H Ko & J H L Hansen (eds), Proceedings of Interspeech 2022. Interspeech - Annual Conference of the International Speech Communication Association, pp. 3388-3392. https://doi.org/10.21437/Interspeech.2022-10167","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W242082043","https://openalex.org/W399112545","https://openalex.org/W2241737282","https://openalex.org/W2745644908","https://openalex.org/W2973177710","https://openalex.org/W3015783745","https://openalex.org/W3024869864","https://openalex.org/W3113822960","https://openalex.org/W3150572638","https://openalex.org/W3151309757","https://openalex.org/W3167533889","https://openalex.org/W3197824033","https://openalex.org/W3197934793","https://openalex.org/W3211602610","https://openalex.org/W3213713237","https://openalex.org/W4248634141","https://openalex.org/W4299687266","https://openalex.org/W4399569456"],"related_works":["https://openalex.org/W3149582125","https://openalex.org/W2349468610","https://openalex.org/W2465421051","https://openalex.org/W2181715843","https://openalex.org/W652196294","https://openalex.org/W2395605663","https://openalex.org/W1984347656","https://openalex.org/W2772686614","https://openalex.org/W4200068392","https://openalex.org/W231741463"],"abstract_inverted_index":{"For":[0],"isolated":[1],"utterances,":[2],"speech":[3,24,47,78,140,153],"synthesis":[4,40,79],"quality":[5],"has":[6],"improved":[7],"immensely":[8],"thanks":[9],"to":[10,27,29,62,81,118],"the":[11,39,115,176],"use":[12],"of":[13,41,122,138,151,160],"sequence-to-sequence":[14],"models.":[15],"However,":[16],"these":[17,64],"models":[18],"are":[19,53,75],"generally":[20],"trained":[21,134,147],"on":[22,38,101,135,148],"read":[23,57],"and":[25,43,125,145,162],"fail":[26],"generalise":[28],"unseen":[30],"speaking":[31],"styles.":[32],"Recently,":[33],"more":[34,180],"re-search":[35],"is":[36],"focused":[37],"expressive":[42],"conversa-tional":[44],"speech.":[45,58],"Conversational":[46],"contains":[48],"many":[49,71],"prosodic":[50,65],"phenomena":[51],"that":[52,155,175],"not":[54],"present":[55],"in":[56],"We":[59,85,113,128],"would":[60],"like":[61],"learn":[63],"patterns":[66],"from":[67,104,111,141,154,170],"data,":[68],"but":[69],"unfortunately,":[70],"large":[72],"conversational":[73,94],"corpora":[74],"unsuitable":[76],"for":[77,96],"due":[80],"low":[82],"audio":[83],"quality.":[84],"investigate":[86],"whether":[87],"a":[88,97,120,142],"data":[89,103,110,117],"mixing":[90],"strategy":[91],"can":[92],"improve":[93],"prosody":[95],"target":[98],"voice":[99],"based":[100],"monologue":[102,139,152],"audiobooks":[105],"by":[106,165],"adding":[107],"real":[108],"con-versational":[109],"podcasts.":[112],"filter":[114],"podcast":[116],"create":[119],"set":[121],"26k":[123],"question":[124,182],"answer":[126],"pairs.":[127],"evaluate":[129],"two":[130],"FastPitch":[131],"models:":[132],"one":[133],"20":[136],"hours":[137,150,159],"single":[143],"speaker,":[144],"another":[146],"5":[149],"speaker":[156],"plus":[157],"15":[158],"ques-tions":[161],"answers":[163],"spoken":[164],"nearly":[166],"15k":[167],"speakers.":[168],"Results":[169],"three":[171],"listening":[172],"tests":[173],"show":[174],"second":[177],"model":[178],"generates":[179],"preferred":[181],"prosody.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}