{"id":"https://openalex.org/W2269105564","doi":"https://doi.org/10.21437/interspeech.2012-357","title":"Combining multiple high quality corpora for improving HMM-TTS","display_name":"Combining multiple high quality corpora for improving HMM-TTS","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W2269105564","doi":"https://doi.org/10.21437/interspeech.2012-357","mag":"2269105564"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-357","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031222393","display_name":"Vincent Wan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127366","display_name":"Toshiba (South Korea)","ror":"https://ror.org/02mavrn48","country_code":"KR","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210127366"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Vincent Wan","raw_affiliation_strings":["Toshiba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba","institution_ids":["https://openalex.org/I4210127366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071418947","display_name":"Javier Latorre","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127366","display_name":"Toshiba (South Korea)","ror":"https://ror.org/02mavrn48","country_code":"KR","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210127366"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Javier Latorre","raw_affiliation_strings":["Toshiba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba","institution_ids":["https://openalex.org/I4210127366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058000820","display_name":"K. K. Chin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127366","display_name":"Toshiba (South Korea)","ror":"https://ror.org/02mavrn48","country_code":"KR","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210127366"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"K. K. Chin","raw_affiliation_strings":["Toshiba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba","institution_ids":["https://openalex.org/I4210127366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070433127","display_name":"Langzhou Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127366","display_name":"Toshiba (South Korea)","ror":"https://ror.org/02mavrn48","country_code":"KR","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210127366"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Langzhou Chen","raw_affiliation_strings":["Toshiba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba","institution_ids":["https://openalex.org/I4210127366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050766679","display_name":"Mark Gales","orcid":"https://orcid.org/0000-0002-5311-8219"},"institutions":[{"id":"https://openalex.org/I4210127366","display_name":"Toshiba (South Korea)","ror":"https://ror.org/02mavrn48","country_code":"KR","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210127366"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Mark J. F. Gales","raw_affiliation_strings":["Toshiba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba","institution_ids":["https://openalex.org/I4210127366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003420204","display_name":"Heiga Zen","orcid":"https://orcid.org/0000-0002-8959-5471"},"institutions":[{"id":"https://openalex.org/I4210127366","display_name":"Toshiba (South Korea)","ror":"https://ror.org/02mavrn48","country_code":"KR","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210127366"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Heiga Zen","raw_affiliation_strings":["Toshiba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba","institution_ids":["https://openalex.org/I4210127366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111076409","display_name":"Kate Knill","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127366","display_name":"Toshiba (South Korea)","ror":"https://ror.org/02mavrn48","country_code":"KR","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210127366"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kate Knill","raw_affiliation_strings":["Toshiba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba","institution_ids":["https://openalex.org/I4210127366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112250968","display_name":"Masami Akamine","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127366","display_name":"Toshiba (South Korea)","ror":"https://ror.org/02mavrn48","country_code":"KR","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210127366"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Masami Akamine","raw_affiliation_strings":["Toshiba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba","institution_ids":["https://openalex.org/I4210127366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210127366"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1135","last_page":"1138"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9965000152587891,"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":0.9944999814033508,"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/computer-science","display_name":"Computer science","score":0.8015962839126587},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7945231199264526},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7445324659347534},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6260087490081787},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.597460150718689},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.41754838824272156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35430872440338135}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8015962839126587},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7945231199264526},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7445324659347534},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6260087490081787},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.597460150718689},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.41754838824272156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35430872440338135},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2012-357","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},{"id":"pmh:oai:generic.eprints.org:593289","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/593289/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","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":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.75}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W126988493","https://openalex.org/W2025638820","https://openalex.org/W2069631319","https://openalex.org/W2114659828","https://openalex.org/W2142980177","https://openalex.org/W2153914468","https://openalex.org/W2158120945","https://openalex.org/W2283817422","https://openalex.org/W2292984643","https://openalex.org/W3031363333"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861","https://openalex.org/W2904846757"],"abstract_inverted_index":{"The":[0],"most":[1],"reliable":[2],"way":[3],"to":[4,11,40,50,102,123],"build":[5],"synthetic":[6],"voices":[7,84],"for":[8],"end-products":[9],"is":[10,70,90],"start":[12],"with":[13],"high":[14,47],"quality":[15,48,60,119],"recordings":[16],"from":[17],"professional":[18],"voice":[19,28,59,118],"talents.":[20],"This":[21],"paper":[22],"describes":[23],"the":[24],"application":[25,34],"of":[26,35,45,54,110,126],"average":[27],"models":[29],"(AVMs)":[30],"and":[31,56,78],"a":[32,42,103,107,115],"novel":[33],"cluster":[36],"adaptive":[37],"training":[38,74],"(CAT)":[39],"combine":[41],"small":[43],"number":[44],"these":[46],"corpora":[49],"make":[51],"best":[52],"use":[53],"them":[55],"improve":[57],"overall":[58],"in":[61],"hidden":[62],"Markov":[63],"model":[64],"based":[65],"text-to-speech":[66],"(HMMTTS)":[67],"systems.":[68],"It":[69,89],"shown":[71,92],"that":[72,93],"integrated":[73],"by":[75],"both":[76],"CAT":[77,94,113],"AVM":[79],"approaches,":[80],"yields":[81],"better":[82],"sounding":[83],"than":[85],"speaker":[86],"dependent":[87],"modelling.":[88],"also":[91],"has":[95],"an":[96],"advantage":[97],"over":[98],"AVMs":[99],"when":[100,121],"adapting":[101],"new":[104],"speaker.":[105],"Given":[106],"limited":[108],"amount":[109],"adaptation":[111],"data":[112],"maintains":[114],"much":[116],"higher":[117],"even":[120],"adapted":[122],"tiny":[124],"amounts":[125],"speech.":[127]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
