{"id":"https://openalex.org/W1479948762","doi":"https://doi.org/10.21437/interspeech.2009-491","title":"HMM adaptation and voice conversion for the synthesis of child speech: a comparison","display_name":"HMM adaptation and voice conversion for the synthesis of child speech: a comparison","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W1479948762","doi":"https://doi.org/10.21437/interspeech.2009-491","mag":"1479948762"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-491","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","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/15114909/HMM_adaptation_and_voice_conversion_for_the_synthesis_of_child_speech.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110238677","display_name":"Oliver Watts","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oliver Watts","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["School of Philosophy, Psychology and Language Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Philosophy, Psychology and Language Sciences","institution_ids":[]}]},{"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":["School of Philosophy Psychology and Language Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Philosophy Psychology and Language Sciences","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":[{"id":"https://openalex.org/I121595252","display_name":"Polytechnic University of Puerto Rico","ror":"https://ror.org/01b8jmq89","country_code":"PR","type":"education","lineage":["https://openalex.org/I121595252"]}],"countries":["PR"],"is_corresponding":false,"raw_author_name":"Kay Berkling","raw_affiliation_strings":["Polytechnic University of Puerto Rico, San Juan, Puerto Rico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Polytechnic University of Puerto Rico, San Juan, Puerto Rico","institution_ids":["https://openalex.org/I121595252"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9059,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.79305673,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2627","last_page":"2630"},"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":0.9969000220298767,"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":0.9865999817848206,"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/speech-synthesis","display_name":"Speech synthesis","score":0.8220642805099487},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7836989164352417},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.7775115966796875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7190402150154114},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.690787672996521},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.667894184589386},{"id":"https://openalex.org/keywords/voice-analysis","display_name":"Voice analysis","score":0.47792869806289673},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.46781349182128906},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43946120142936707},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.41738444566726685},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.365037739276886},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33572399616241455},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11292356252670288},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08397617936134338}],"concepts":[{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.8220642805099487},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7836989164352417},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.7775115966796875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7190402150154114},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.690787672996521},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.667894184589386},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.47792869806289673},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.46781349182128906},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43946120142936707},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.41738444566726685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.365037739276886},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33572399616241455},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11292356252670288},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08397617936134338},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2009-491","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/3d39a521-0285-46d5-885f-fcd1bf8abe98","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/3d39a521-0285-46d5-885f-fcd1bf8abe98","pdf_url":"https://www.pure.ed.ac.uk/ws/files/15114909/HMM_adaptation_and_voice_conversion_for_the_synthesis_of_child_speech.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:CiteSeerX.psu:10.1.1.148.2109","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.148.2109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.ed.ac.uk/downloads/publications/2009/child_synthesis_2009.pdf","raw_type":"text"},{"id":"pmh:oai:era.ed.ac.uk:1842/3923","is_oa":false,"landing_page_url":"http://hdl.handle.net/1842/3923","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":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/3d39a521-0285-46d5-885f-fcd1bf8abe98","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/3d39a521-0285-46d5-885f-fcd1bf8abe98","pdf_url":"https://www.pure.ed.ac.uk/ws/files/15114909/HMM_adaptation_and_voice_conversion_for_the_synthesis_of_child_speech.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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.49000000953674316}],"awards":[],"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/W1479948762.pdf","grobid_xml":"https://content.openalex.org/works/W1479948762.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W1567666748","https://openalex.org/W1812022101","https://openalex.org/W2049686551","https://openalex.org/W2120605154","https://openalex.org/W2156142001","https://openalex.org/W2165856656","https://openalex.org/W2170980774","https://openalex.org/W2400063444","https://openalex.org/W2406017614","https://openalex.org/W3216401400"],"related_works":["https://openalex.org/W234770729","https://openalex.org/W2588431733","https://openalex.org/W2391796527","https://openalex.org/W2387179309","https://openalex.org/W2388979876","https://openalex.org/W4245668640","https://openalex.org/W2032960563","https://openalex.org/W2142993035","https://openalex.org/W2899044948","https://openalex.org/W2336057175"],"abstract_inverted_index":{"This":[0,53],"study":[1],"compares":[2],"two":[3],"different":[4],"methodologies":[5],"for":[6],"producing":[7],"data-driven":[8],"synthesis":[9],"of":[10,23,49,59,67,84,87],"child":[11,51,124],"speech":[12,22,89,92,128,131],"from":[13,93],"existing":[14,29,69],"systems":[15,99],"that":[16],"have":[17],"been":[18],"trained":[19],"on":[20],"the":[21,46,57,65,85,94,97,113],"adults.":[24],"On":[25],"one":[26],"hand,":[27],"an":[28,68],"statistical":[30,126],"parametric":[31,127],"synthesiser":[32,72],"is":[33,54,106],"transformed":[34],"using":[35],"model":[36],"adaptation":[37],"techniques,":[38],"informed":[39],"by":[40,119],"linguistic":[41,76],"and":[42],"prosodic":[43,78],"knowledge,":[44],"to":[45,63,90,112],"speaker":[47],"characteristics":[48],"a":[50,81],"speaker.":[52],"compared":[55],"with":[56,73],"application":[58],"voice":[60,133],"conversion":[61],"techniques":[62],"convert":[64],"output":[66],"waveform":[70],"concatenation":[71],"no":[74],"explicit":[75],"or":[77],"knowledge.":[79],"In":[80],"subjective":[82],"evaluation":[83],"similarity":[86],"synthetic":[88],"natural":[91],"target":[95],"speaker,":[96],"HMM-based":[98,130],"evaluated":[100],"are":[101],"generally":[102],"preferred,":[103],"although":[104],"this":[105],"at":[107],"least":[108],"in":[109],"part":[110],"due":[111],"higher":[114],"dimensional":[115],"acoustic":[116],"features":[117],"supported":[118],"these":[120],"techniques.":[121],"Index":[122],"Terms:":[123],"speech,":[125],"synthesis,":[129,132],"conversion,":[134],"HTS,":[135],"Average":[136],"Voice":[137],"Models,":[138],"Festival":[139]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}