{"id":"https://openalex.org/W315928314","doi":"https://doi.org/10.21437/eurospeech.2003-129","title":"My voice, your prosody: sharing a speaker specific prosody model across speakers in unit selection TTS","display_name":"My voice, your prosody: sharing a speaker specific prosody model across speakers in unit selection TTS","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W315928314","doi":"https://doi.org/10.21437/eurospeech.2003-129","mag":"315928314"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-129","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.pure.ed.ac.uk/ws/files/27203325/e03_0321.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007820415","display_name":"Matthew P. Aylett","orcid":"https://orcid.org/0000-0001-7057-0525"},"institutions":[{"id":"https://openalex.org/I4210145895","display_name":"Restorix Health","ror":"https://ror.org/04nzdnk52","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210145895"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Matthew Aylett","raw_affiliation_strings":["Rhetorical Systems Ltd"],"affiliations":[{"raw_affiliation_string":"Rhetorical Systems Ltd","institution_ids":["https://openalex.org/I4210145895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113495803","display_name":"Justin Fackrell","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145895","display_name":"Restorix Health","ror":"https://ror.org/04nzdnk52","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210145895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin Fackrell","raw_affiliation_strings":["Rhetorical Systems Ltd"],"affiliations":[{"raw_affiliation_string":"Rhetorical Systems Ltd","institution_ids":["https://openalex.org/I4210145895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060410040","display_name":"Peter Rutten","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145895","display_name":"Restorix Health","ror":"https://ror.org/04nzdnk52","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210145895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Rutten","raw_affiliation_strings":["Rhetorical Systems Ltd"],"affiliations":[{"raw_affiliation_string":"Rhetorical Systems Ltd","institution_ids":["https://openalex.org/I4210145895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5007820415"],"corresponding_institution_ids":["https://openalex.org/I4210145895"],"apc_list":null,"apc_paid":null,"fwci":1.8719,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.86824852,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"321","last_page":"324"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9976999759674072,"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/T12031","display_name":"Speech and dialogue systems","score":0.996399998664856,"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":0.9485002756118774},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7094807028770447},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7024716734886169},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6289176940917969},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.45822039246559143},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2992827892303467},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.24186795949935913}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.9485002756118774},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7094807028770447},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7024716734886169},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6289176940917969},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.45822039246559143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2992827892303467},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.24186795949935913}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/eurospeech.2003-129","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/38d7fce5-8ca2-40a4-a958-6e7e4b5c2a09","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/38d7fce5-8ca2-40a4-a958-6e7e4b5c2a09","pdf_url":"https://www.pure.ed.ac.uk/ws/files/27203325/e03_0321.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/38d7fce5-8ca2-40a4-a958-6e7e4b5c2a09","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/38d7fce5-8ca2-40a4-a958-6e7e4b5c2a09","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":"Aylett, M P, Fackrell, J & Rutten, P 2003, My Voice, Your Prosody: Sharing a Speaker Specific Prosody Model Across Speakers in Unit Selection TTS. in 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003 - INTERSPEECH 2003, Geneva, Switzerland, September 1-4, 2003. pp. 321-324, 8th European Conference on Speech Communication and Technology (Eurospeech 2003), Geneva, Switzerland, 1/09/03. < http://www.isca-speech.org/archive/eurospeech_2003/e03_0321.html >","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/38d7fce5-8ca2-40a4-a958-6e7e4b5c2a09","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/38d7fce5-8ca2-40a4-a958-6e7e4b5c2a09","pdf_url":"https://www.pure.ed.ac.uk/ws/files/27203325/e03_0321.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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W315928314.pdf","grobid_xml":"https://content.openalex.org/works/W315928314.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W8081149","https://openalex.org/W169530861","https://openalex.org/W182831726","https://openalex.org/W1500192039","https://openalex.org/W1526376014","https://openalex.org/W1562811233","https://openalex.org/W1689445748","https://openalex.org/W2116043656","https://openalex.org/W2141683451","https://openalex.org/W4235613087"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2355553914","https://openalex.org/W149862513","https://openalex.org/W2347684782","https://openalex.org/W4320472397","https://openalex.org/W2401269021","https://openalex.org/W2145654520","https://openalex.org/W2546089952","https://openalex.org/W2140022733"],"abstract_inverted_index":{"Data":[0],"sparsity":[1],"is":[2,19,86],"a":[3,20,38,44,52,62,73,90,109,128,139,143,152,229,246,259,276],"major":[4],"problem":[5],"for":[6,157,166,243,324],"data":[7,16],"driven":[8],"prosodic":[9,15,154,196],"models.":[10,215],"Being":[11],"able":[12],"to":[13,23,88,116,147,178,189,221,331],"share":[14],"across":[17],"speakers":[18],"potential":[21,30],"solution":[22,31],"this":[24,29],"problem.":[25],"This":[26],"paper":[27],"explores":[28],"by":[32],"addressing":[33],"two":[34],"questions:":[35],"1)":[36],"Does":[37],"larger":[39,65],"less":[40,297],"sparse":[41,54,75],"model":[42,55,66,76,93,261,278,293],"from":[43,57,78,194,262,280,318],"different":[45,63],"speaker":[46,130,141,148,167,173,179,209,265],"produce":[47,89,272,295],"more":[48,68,269,300],"natural":[49,270,298],"speech":[50,238],"than":[51,72,275],"small":[53,74],"built":[56,77],"the":[58,79,119,122,163,183,207,213,281,303],"original":[59,80],"speaker?":[60,81],"2)Does":[61],"speaker's":[64,98,283],"generate":[67],"unit":[69,83],"selection":[70,84],"errors":[71,244,274,301],"A":[82],"approach":[85],"used":[87],"lazy":[91],"learning":[92],"of":[94,121,212],"three":[95,188,214,247],"English":[96],"RP":[97],"f0":[99,145],"and":[100,150,159,172,181,201,210,226,299,310,320,328],"durational":[101],"parameters.":[102],"Speaker":[103,125,136],"1":[104,149,180],"(the":[105],"target":[106,208],"speaker)":[107],"had":[108],"much":[110],"smaller":[111,277],"database":[112],"(approximately":[113],"one":[114,117],"quarter":[115],"fifth":[118],"size)":[120],"other":[123],"two.":[124],"2":[126,168],"was":[127,138],"female":[129],"with":[131,142,151],"frequent":[132],"mid":[133],"phrase":[134],"rises.":[135],"3":[137,174],"male":[140],"similar":[144],"range":[146],"measured":[153],"style":[155],"suitable":[156],"news":[158],"financial":[160],"text.<br/><br/>We":[161],"apply":[162],"models":[164],"created":[165],"(an":[169,175],"inappropriate":[170,292],"model)":[171,177],"appropriate":[176,264],"compare":[182],"results.":[184],"Three":[185],"passages":[186],"(of":[187],"four":[190],"sentences":[191],"in":[192,302,307],"length)":[193],"challenging":[195],"genres":[197],"(news":[198],"report,":[199],"poetry":[200],"personal":[202],"email)":[203],"were":[204,219],"synthesised":[205,217],"using":[206,228],"each":[211,241],"The":[216],"utterances":[218],"played":[220],"15":[222],"native":[223],"english":[224],"subjects":[225],"rated":[227,240],"5":[230],"point":[231,248],"MOS":[232],"scale.":[233],"In":[234,286],"addition,":[235],"7":[236],"experienced":[237],"engineers":[239],"word":[242],"on":[245],"scale:":[249],"1.":[250],"Acceptable,":[251],"2.":[252],"Poor,":[253],"3.":[254],"Unacceptable.<br/><br/>The":[255],"results":[256],"suggest":[257,313],"that":[258,290,321],"large":[260],"an":[263,291],"does":[266,294],"not":[267],"sound":[268],"or":[271],"fewer":[273],"generated":[279],"individual":[282],"own":[284],"data.":[285],"addition":[287],"it":[288],"shows":[289],"both":[296,308,314,325],"speech.":[304],"High":[305],"variance":[306],"subject":[309],"materials":[311],"analysis":[312],"tests":[315],"are":[316],"far":[317],"ideal":[319],"evaluation":[322],"techniques":[323],"error":[326],"rate":[327],"naturalness":[329],"need":[330],"improve.":[332]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}