{"id":"https://openalex.org/W126988493","doi":"https://doi.org/10.21437/interspeech.2012-289","title":"Speech factorization for HMM-TTS based on cluster adaptive training","display_name":"Speech factorization for HMM-TTS based on cluster adaptive training","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W126988493","doi":"https://doi.org/10.21437/interspeech.2012-289","mag":"126988493"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-289","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-289","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/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/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/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/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/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/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":28,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"971","last_page":"974"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9966999888420105,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7745330333709717},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.718401312828064},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5855071544647217},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5851560235023499},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5327121615409851},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5070004463195801},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4659038186073303},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.4599314033985138},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4481351971626282},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.42117515206336975},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3621799349784851},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14590123295783997},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.06925225257873535}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7745330333709717},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.718401312828064},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5855071544647217},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5851560235023499},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5327121615409851},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5070004463195801},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4659038186073303},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.4599314033985138},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4481351971626282},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42117515206336975},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3621799349784851},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14590123295783997},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.06925225257873535},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2012-289","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-289","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:593287","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/593287/","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W51255321","https://openalex.org/W83586041","https://openalex.org/W113106864","https://openalex.org/W2025638820","https://openalex.org/W2042600255","https://openalex.org/W2102146461","https://openalex.org/W2148846882","https://openalex.org/W2153914468","https://openalex.org/W2158972663","https://openalex.org/W2169166781","https://openalex.org/W2269105564","https://openalex.org/W2292984643"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W2904846757","https://openalex.org/W175280642","https://openalex.org/W2688184458","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021"],"abstract_inverted_index":{"This":[0],"paper":[1,19,109],"presents":[2],"a":[3,35,45,71,85],"novel":[4],"approach":[5,94],"to":[6,26,97],"factorize":[7,27],"and":[8,30,55,78,104],"control":[9,52],"different":[10,46,105],"speech":[11,39,99,124],"factors":[12],"in":[13,70],"HMM-based":[14],"TTS":[15],"systems.":[16],"In":[17],"this":[18],"cluster":[20],"adaptive":[21],"training":[22,91],"(CAT)":[23],"is":[24,95],"used":[25],"speaker":[28,53,77,86],"identity":[29,54],"expressiveness":[31,56],"(i.e.":[32],"emotion).":[33],"Within":[34],"CAT":[36],"framework,":[37],"each":[38,64],"factor":[40],"can":[41,51],"be":[42],"modelled":[43],"by":[44,58],"set":[47],"of":[48,76,113,122],"clusters.":[49],"Users":[50],"independently":[57],"modifying":[59],"the":[60,93,108,114,120],"weights":[61,67],"associated":[62],"with":[63,100],"set.":[65],"These":[66],"are":[68,80],"defined":[69],"continuous":[72],"space,":[73],"so":[74],"variations":[75],"emotion":[79],"also":[81],"continuous.":[82],"Additionally,":[83],"given":[84],"which":[87],"has":[88],"only":[89],"neutral-style":[90],"data,":[92],"able":[96],"synthesise":[98],"that":[101],"speaker\u2019s":[102],"voice":[103],"expressions.":[106],"Lastly,":[107],"discusses":[110],"how":[111],"generalization":[112],"basic":[115],"factorization":[116],"concept":[117],"could":[118],"allow":[119],"production":[121],"expressive":[123],"from":[125],"neutral":[126],"voices":[127],"for":[128],"other":[129],"HMM-TTS":[130],"systems":[131],"not":[132],"based":[133],"on":[134],"CAT.":[135]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":12},{"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"}