{"id":"https://openalex.org/W2119712087","doi":"https://doi.org/10.1109/jstsp.2014.2305919","title":"Contextual Additive Structure for HMM-Based Speech Synthesis","display_name":"Contextual Additive Structure for HMM-Based Speech Synthesis","publication_year":2014,"publication_date":"2014-02-12","ids":{"openalex":"https://openalex.org/W2119712087","doi":"https://doi.org/10.1109/jstsp.2014.2305919","mag":"2119712087"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2014.2305919","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2014.2305919","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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 Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"type":"article","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/A5062895056","display_name":"Shinji Takaki","orcid":"https://orcid.org/0000-0001-7294-7699"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinji Takaki","raw_affiliation_strings":["Department of Computer Science and Enineering, Nagoya Institute of Technology, Nagoya, Japan","[Department of Computer Science and Enineering, Nagoya Institute of Technology, Nagoya, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Enineering, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"[Department of Computer Science and Enineering, Nagoya Institute of Technology, Nagoya, Japan]","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023240652","display_name":"Yoshihiko Nankaku","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshihiko Nankaku","raw_affiliation_strings":["Department of Computer Science and Enineering, Nagoya Institute of Technology, Nagoya, Japan","[Department of Computer Science and Enineering, Nagoya Institute of Technology, Nagoya, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Enineering, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"[Department of Computer Science and Enineering, Nagoya Institute of Technology, Nagoya, Japan]","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103023678","display_name":"Keiichi Tokuda","orcid":"https://orcid.org/0000-0001-6143-0133"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiichi Tokuda","raw_affiliation_strings":["Department of Computer Science and Enineering, Nagoya Institute of Technology, Nagoya, Japan","[Department of Computer Science and Enineering, Nagoya Institute of Technology, Nagoya, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Enineering, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"[Department of Computer Science and Enineering, Nagoya Institute of Technology, Nagoya, Japan]","institution_ids":["https://openalex.org/I197274945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197274945"],"apc_list":null,"apc_paid":null,"fwci":1.6567,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.87857753,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"8","issue":"2","first_page":"229","last_page":"238"},"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":0.9983000159263611,"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":0.9966999888420105,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7672468423843384},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7631291747093201},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.649884819984436},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6167958378791809},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5468035936355591},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4982137680053711},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4756964147090912},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46457207202911377},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44273272156715393},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3214927017688751}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7672468423843384},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7631291747093201},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.649884819984436},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6167958378791809},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5468035936355591},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4982137680053711},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4756964147090912},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46457207202911377},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44273272156715393},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3214927017688751},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2014.2305919","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2014.2305919","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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 Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G3727397721","display_name":"aaa","funder_award_id":"25280061","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4372364119","display_name":"A speech interaction system created by \"speech\"","funder_award_id":"26540083","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G585093916","display_name":"Development of statistically consistent voice conversion techniques based on joint feature modeling","funder_award_id":"24700166","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W4362787","https://openalex.org/W35069904","https://openalex.org/W1514737389","https://openalex.org/W1600722501","https://openalex.org/W1963627370","https://openalex.org/W2049686551","https://openalex.org/W2069631319","https://openalex.org/W2093450784","https://openalex.org/W2099352211","https://openalex.org/W2103859372","https://openalex.org/W2106689794","https://openalex.org/W2115222111","https://openalex.org/W2116952749","https://openalex.org/W2143361917","https://openalex.org/W2144139079","https://openalex.org/W2149017325","https://openalex.org/W2154920538","https://openalex.org/W2158069733","https://openalex.org/W2166823384","https://openalex.org/W2395318165","https://openalex.org/W2396713766","https://openalex.org/W2740537351","https://openalex.org/W4236088841","https://openalex.org/W6680838236","https://openalex.org/W6682272363","https://openalex.org/W6682918086","https://openalex.org/W6712520822"],"related_works":["https://openalex.org/W2181773877","https://openalex.org/W2038801705","https://openalex.org/W2110108310","https://openalex.org/W155946340","https://openalex.org/W2904846757","https://openalex.org/W2968379855","https://openalex.org/W2168531172","https://openalex.org/W2093265061","https://openalex.org/W2166752834","https://openalex.org/W176513972"],"abstract_inverted_index":{"This":[0],"paper":[1,61],"proposes":[2,62],"a":[3,69],"spectral":[4],"modeling":[5],"technique":[6],"based":[7],"on":[8],"an":[9],"additive":[10,20],"structure":[11,21,79],"of":[12,41,53],"context":[13,31,43,51],"dependencies":[14,26],"for":[15,48],"HMM-based":[16,85],"speech":[17,54,86,92],"synthesis.":[18,55],"Contextual":[19],"models":[22,80],"can":[23,81],"represent":[24],"complicated":[25],"between":[27],"acoustic":[28],"features":[29],"and":[30,68,91],"labels":[32,52],"using":[33,73,88],"multiple":[34],"decision":[35],"trees.":[36],"However,":[37],"the":[38,42,49,74,102,106],"computational":[39],"complexity":[40],"clustering":[44],"is":[45],"too":[46],"high":[47],"full":[50],"To":[56],"overcome":[57],"this":[58,60],"problem,":[59],"two":[63],"approaches;":[64],"covariance":[65],"parameter":[66],"tying":[67],"likelihood":[70],"calculation":[71],"algorithm":[72],"matrix":[75],"inversion":[76],"lemma.":[77],"Additive":[78],"be":[82,96],"applied":[83],"to":[84],"synthesis":[87],"these":[89],"techniques":[90],"quality":[93],"would":[94],"significantly":[95],"improved.":[97],"Experimental":[98],"results":[99],"show":[100],"that":[101],"proposed":[103],"method":[104],"outperforms":[105],"conventional":[107],"one":[108],"in":[109],"subjective":[110],"listening":[111],"tests.":[112]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}