{"id":"https://openalex.org/W2156690084","doi":"https://doi.org/10.1109/tasl.2009.2035029","title":"Synthesis of Child Speech With HMM Adaptation and Voice Conversion","display_name":"Synthesis of Child Speech With HMM Adaptation and Voice Conversion","publication_year":2009,"publication_date":"2009-11-03","ids":{"openalex":"https://openalex.org/W2156690084","doi":"https://doi.org/10.1109/tasl.2009.2035029","mag":"2156690084"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2009.2035029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2009.2035029","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/9cb49fc8-db55-4769-88a3-9e19d45f01fc","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":["Centre of Speech Technology Research, University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre of Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"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":["Centre of Speech Technology Research, University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre of Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","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":["Centre of Speech Technology Research, University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre of Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067913033","display_name":"Kay Berkling","orcid":"https://orcid.org/0000-0003-1186-5678"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kay Berkling","raw_affiliation_strings":["Inline Internet Online Dienste GmbH, Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inline Internet Online Dienste GmbH, Karlsruhe, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8119,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.88300537,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"18","issue":"5","first_page":"1005","last_page":"1016"},"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":0.9990000128746033,"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":0.9933000206947327,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8748244047164917},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7549377679824829},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7217150330543518},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6840463876724243},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5974360704421997},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5375475883483887},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08736720681190491},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07376205921173096},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06684967875480652}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8748244047164917},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7549377679824829},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7217150330543518},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6840463876724243},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5974360704421997},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5375475883483887},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08736720681190491},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07376205921173096},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06684967875480652},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1109/tasl.2009.2035029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2009.2035029","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/9cb49fc8-db55-4769-88a3-9e19d45f01fc","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/9cb49fc8-db55-4769-88a3-9e19d45f01fc","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Watts, O, Yamagishi, J, King, S & Berkling, K 2010, 'Synthesis of Child Speech With HMM Adaptation and Voice Conversion', IEEE Transactions on Audio, Speech and Language Processing, vol. 18, no. 5, pp. 1005-1016. https://doi.org/10.1109/TASL.2009.2035029","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:era.ed.ac.uk:1842/3725","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/3725","pdf_url":"https://era.ed.ac.uk/bitstream/1842/3725/1/YamagishiJ_Synthesis%20of%20Child%20Speech.pdf","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","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":null,"raw_type":"Article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.294.4105","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.294.4105","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.inf.ed.ac.uk/downloads/publications/2010/YamagishiJ_SynthesisofChildSpeech.pdf","raw_type":"text"},{"id":"pmh:oai:era.ed.ac.uk:1842/4530","is_oa":false,"landing_page_url":"http://hdl.handle.net/1842/4530","pdf_url":null,"source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","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":null,"raw_type":"Article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/9cb49fc8-db55-4769-88a3-9e19d45f01fc","is_oa":false,"landing_page_url":null,"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":""},{"id":"pmh:oai:pure.ed.ac.uk:publications/9cb49fc8-db55-4769-88a3-9e19d45f01fc","is_oa":true,"landing_page_url":"http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5299003&tag=1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":"Watts, O, Yamagishi, J, King, S & Berkling, K 2010, 'Synthesis of Child Speech With HMM Adaptation and Voice Conversion', IEEE Transactions on Audio, Speech and Language Processing, vol. 18, no. 5, pp. 1005-1016. https://doi.org/10.1109/TASL.2009.2035029","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/9cb49fc8-db55-4769-88a3-9e19d45f01fc","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/9cb49fc8-db55-4769-88a3-9e19d45f01fc","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Watts, O, Yamagishi, J, King, S & Berkling, K 2010, 'Synthesis of Child Speech With HMM Adaptation and Voice Conversion', IEEE Transactions on Audio, Speech and Language Processing, vol. 18, no. 5, pp. 1005-1016. https://doi.org/10.1109/TASL.2009.2035029","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"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":31,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W146603069","https://openalex.org/W1479948762","https://openalex.org/W1564152904","https://openalex.org/W1567666748","https://openalex.org/W1592103878","https://openalex.org/W1812022101","https://openalex.org/W1984905644","https://openalex.org/W1994888226","https://openalex.org/W2042691334","https://openalex.org/W2049686551","https://openalex.org/W2116046013","https://openalex.org/W2117418893","https://openalex.org/W2120605154","https://openalex.org/W2129142580","https://openalex.org/W2153914468","https://openalex.org/W2156142001","https://openalex.org/W2160084280","https://openalex.org/W2165856656","https://openalex.org/W2170980774","https://openalex.org/W2400063444","https://openalex.org/W2402261002","https://openalex.org/W2406017614","https://openalex.org/W2915628810","https://openalex.org/W3216401400","https://openalex.org/W6603838645","https://openalex.org/W6638317995","https://openalex.org/W6677333272","https://openalex.org/W6712610176","https://openalex.org/W6714191056","https://openalex.org/W6759752890"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1521297879","https://openalex.org/W2036150633","https://openalex.org/W3184123547","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W2536059291"],"abstract_inverted_index":{"The":[0],"synthesis":[1],"of":[2,11,17,52,64,80,100],"child":[3,108],"speech":[4],"presents":[5],"challenges":[6],"both":[7,70],"in":[8,14,111],"the":[9,15,32,65,98,101,112,123],"collection":[10],"data":[12,56],"and":[13,54,72,76],"building":[16],"a":[18,27],"synthesizer":[19,30,66],"from":[20,88],"that":[21],"data.":[22,81],"We":[23],"chose":[24],"to":[25,46,93,97],"build":[26],"statistical":[28],"parametric":[29],"using":[31,69,77,122],"hidden":[33],"Markov":[34],"model":[35],"(HMM)-based":[36],"system":[37],"HTS,":[38],"as":[39],"this":[40],"technique":[41],"has":[42],"previously":[43],"been":[44],"shown":[45],"perform":[47],"well":[48],"for":[49,55,137],"limited":[50],"amounts":[51,79],"data,":[53,131],"collected":[57],"under":[58],"imperfect":[59],"conditions.":[60],"Six":[61],"different":[62],"configurations":[63],"were":[67,91],"compared,":[68],"speaker-dependent":[71,109],"speaker-adaptive":[73],"modeling":[74],"techniques,":[75],"varying":[78],"For":[82],"comparison":[83],"with":[84,128],"HMM":[85,114,139],"adaptation,":[86],"techniques":[87,120],"voice":[89,117,142],"conversion":[90,118,143],"used":[92],"transform":[94],"existing":[95],"synthesizers":[96],"characteristics":[99],"target":[102,125],"speaker.":[103],"Speaker-adaptive":[104],"voices":[105,110],"generally":[106],"outperformed":[107,116],"evaluation.":[113],"adaptation":[115,130,140],"style":[119],"when":[121],"full":[124],"speaker":[126],"corpus;":[127],"fewer":[129],"however,":[132],"no":[133],"significant":[134],"listener":[135],"preference":[136],"either":[138],"or":[141],"methods":[144],"was":[145],"found.":[146]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}