{"id":"https://openalex.org/W1854592333","doi":null,"title":"Combining Statistical Parameteric Speech Synthesis and Unit-Selection for Automatic Voice Cloning","display_name":"Combining Statistical Parameteric Speech Synthesis and Unit-Selection for Automatic Voice Cloning","publication_year":2008,"publication_date":"2008-09-01","ids":{"openalex":"https://openalex.org/W1854592333","mag":"1854592333"},"language":"en","primary_location":{"id":"pmh:oai:era.ed.ac.uk:1842/3882","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/3882","pdf_url":"http://hdl.handle.net/1842/3882","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"Conference Paper"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1842/3882","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955","observed_orcids":["https://orcid.org/0000-0003-2752-3955"]},"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":"Junichi Yamagishi","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":"https://orcid.org/0000-0003-2752-3955","affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007820415","display_name":"Matthew P. Aylett","orcid":"https://orcid.org/0000-0001-7057-0525","observed_orcids":["https://orcid.org/0000-0001-7057-0525"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthew P. Aylett","raw_affiliation_strings":["School of Philosophy, Psychology and Language Sciences"],"raw_orcid":"https://orcid.org/0000-0001-7057-0525","affiliations":[{"raw_affiliation_string":"School of Philosophy, Psychology and Language Sciences","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7886,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.64648172,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":9.999999747378752e-05,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.0,"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/voice-cloning","display_name":"voice cloning","score":0.8379999995231628},{"id":"https://openalex.org/keywords/statistical-parametric-speech-synthesis","display_name":"statistical parametric speech synthesis","score":0.9319999814033508},{"id":"https://openalex.org/keywords/unit-selection-speech-synthesis","display_name":"unit selection speech synthesis","score":0.8399999737739563},{"id":"https://openalex.org/keywords/hmm-based-speech-synthesis","display_name":"HMM-based speech synthesis","score":0.800000011920929},{"id":"https://openalex.org/keywords/prosody","display_name":"prosody","score":0.46700000762939453},{"id":"https://openalex.org/keywords/voice-quality","display_name":"voice quality","score":0.6340000033378601},{"id":"https://openalex.org/keywords/scalability","display_name":"scalability","score":0.4480000138282776},{"id":"https://openalex.org/keywords/laryngectomy","display_name":"laryngectomy","score":0.9359999895095825}],"concepts":[{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6768816709518433},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6485085487365723},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5873235464096069},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.49810004234313965},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.49573859572410583},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.48871803283691406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2980494499206543}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:era.ed.ac.uk:1842/3882","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/3882","pdf_url":"http://hdl.handle.net/1842/3882","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"Conference Paper"},{"id":"mag:1854592333","doi":null,"is_oa":false,"landing_page_url":"http://homepages.inf.ed.ac.uk/matthewa/publications/langtech08.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:era.ed.ac.uk:1842/3882","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/3882","pdf_url":"http://hdl.handle.net/1842/3882","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"Conference Paper"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1544209593","display_name":"Automatically-determined Unit Inventories for Unit Selection Text-to-Speech Synthesis","funder_award_id":"EP/D058139/1","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/W1854592333.pdf","grobid_xml":"https://content.openalex.org/works/W1854592333.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W1541208205","https://openalex.org/W2000513720","https://openalex.org/W2049686551","https://openalex.org/W2116046013","https://openalex.org/W2150658333","https://openalex.org/W2153914468","https://openalex.org/W2165856656","https://openalex.org/W3142087749"],"related_works":["https://openalex.org/W4416508249","https://openalex.org/W7154900028","https://openalex.org/W3095990227","https://openalex.org/W7164496072","https://openalex.org/W366958244","https://openalex.org/W2963192573","https://openalex.org/W3203614938","https://openalex.org/W2337952959","https://openalex.org/W2111468241","https://openalex.org/W7216003815"],"abstract_inverted_index":{"The":[0,30],"ability":[1,31],"to":[2,11,32,77,120,186],"use":[3],"the":[4,61,90,123,126,157,188,197,205,240,251],"recorded":[5],"audio":[6,203],"of":[7,36,63,85,94,125,156,190,196,222,232,253],"a":[8,37,56,64,95,107,173,212],"subject's":[9],"voice":[10,39,59,103,127,189,245],"produce":[12,33,78],"an":[13,160],"open-domain":[14],"synthesis":[15,71],"system":[16,163,176,214],"has":[17,40],"generated":[18],"much":[19],"interest":[20],"both":[21,217],"in":[22,26,60,68],"academic":[23],"research":[24,109],"and":[25,92,140,146,168,172,229,250],"commercial":[27,42,174],"speech":[28,70,86],"technology.":[29],"synthetic":[34,57,79,223],"versions":[35],"subjects":[38],"potential":[41,50],"applications,":[43,52],"such":[44,53],"as":[45,54,98,100],"virtual":[46],"celebrity":[47],"actors,":[48],"or":[49],"clinical":[51],"offering":[55],"replacement":[58],"case":[62],"laryngectomy.":[65],"Recent":[66],"developments":[67],"HMM-based":[69],"have":[72,115,183],"shown":[73,116],"it":[74,117],"is":[75,105,118],"possible":[76,119],"voices":[80,224],"from":[81,204,226],"quite":[82],"small":[83],"amounts":[84],"data.":[87],"However,":[88],"mimicking":[89],"depth":[91],"variation":[93],"speaker's":[96],"prosody":[97],"well":[99],"synthesising":[101],"natural":[102],"quality":[104],"still":[106],"challenging":[108],"problem.":[110],"In":[111,148,207],"contrast,":[112],"unit-selection":[113,175],"systems":[114,182],"strongly":[121],"retain":[122],"character":[124],"but":[128],"only":[129],"with":[130,244],"sufficient":[131],"original":[132],"source":[133],"material.":[134],"Often":[135],"this":[136,149],"runs":[137],"into":[138],"hours":[139],"may":[141],"require":[142],"significant":[143],"manual":[144],"checking":[145],"labelling.":[147],"paper":[150],"we":[151,209],"will":[152,210,237],"present":[153,211],"two":[154],"state":[155],"art":[158],"systems,":[159],"HMM":[161],"based":[162],"HTS-2007,":[164],"developed":[165,178],"by":[166,179],"CSTR":[167],"Nagoya":[169],"Institute":[170],"Technology,":[171],"CereVoice,":[177],"Cereproc.":[180],"Both":[181],"been":[184],"used":[185],"mimic":[187],"George":[191],"W.":[192],"Bush":[193],"(43rd":[194],"president":[195],"United":[198],"States)":[199],"using":[200,247],"freely":[201],"available":[202],"web.":[206],"addition":[208],"hybrid":[213],"which":[215],"combines":[216],"technologies.":[218],"We":[219,236],"demonstrate":[220],"examples":[221],"created":[225],"10,":[227],"40":[228],"210":[230],"minutes":[231],"randomly":[233],"selected":[234],"speech.":[235],"then":[238],"discuss":[239],"underlying":[241],"problems":[242],"associated":[243],"cloning":[246],"found":[248],"audio,":[249],"scalability":[252],"our":[254],"solution.":[255]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-08-29T07:29:34.045763","created_date":"2016-06-24T00:00:00"}