{"id":"https://openalex.org/W1992228106","doi":"https://doi.org/10.1109/jstsp.2013.2283459","title":"A Parameter Generation Algorithm Using Local Variance for HMM-Based Speech Synthesis","display_name":"A Parameter Generation Algorithm Using Local Variance for HMM-Based Speech Synthesis","publication_year":2013,"publication_date":"2013-09-25","ids":{"openalex":"https://openalex.org/W1992228106","doi":"https://doi.org/10.1109/jstsp.2013.2283459","mag":"1992228106"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2013.2283459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2013.2283459","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/A5103144936","display_name":"Takashi Nose","orcid":"https://orcid.org/0000-0001-5403-0019"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Nose","raw_affiliation_strings":["Department of Information Processing, Tokyo Institute of Technology, Yokohama, Japan","Dept. of Inf. Process., Tokyo Inst. of Technol., Yokohama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Processing, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Dept. of Inf. Process., Tokyo Inst. of Technol., Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002206098","display_name":"Vataya Chunwijitra","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Vataya Chunwijitra","raw_affiliation_strings":["Department of Information Processing, Tokyo Institute of Technology, Yokohama, Japan","Dept. of Inf. Process., Tokyo Inst. of Technol., Yokohama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Processing, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Dept. of Inf. Process., Tokyo Inst. of Technol., Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022405100","display_name":"Takao Kobayashi","orcid":"https://orcid.org/0000-0003-0387-8030"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takao Kobayashi","raw_affiliation_strings":["Department of Information Processing, Tokyo Institute of Technology, Yokohama, Japan","Dept. of Inf. Process., Tokyo Inst. of Technol., Yokohama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Processing, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Dept. of Inf. Process., Tokyo Inst. of Technol., Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":3.4074,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.92415689,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"8","issue":"2","first_page":"221","last_page":"228"},"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":0.9976000189781189,"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/T12031","display_name":"Speech and dialogue systems","score":0.993399977684021,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7047920823097229},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6883507966995239},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.676258385181427},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.6080405116081238},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5655431747436523},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5316033363342285},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5229502320289612},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5109990835189819},{"id":"https://openalex.org/keywords/estimation-theory","display_name":"Estimation theory","score":0.5012459754943848},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.4759499728679657},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4144967794418335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3414030075073242},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24699461460113525}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7047920823097229},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6883507966995239},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.676258385181427},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6080405116081238},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5655431747436523},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5316033363342285},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5229502320289612},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5109990835189819},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.5012459754943848},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4759499728679657},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4144967794418335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3414030075073242},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24699461460113525},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2013.2283459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2013.2283459","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":[{"id":"https://metadata.un.org/sdg/4","score":0.44999998807907104,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1573140883","display_name":"Research on advanced robust speech synthesis and its applications to multi-lingual speech communication","funder_award_id":"24300071","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5973663496","display_name":"A study of speech synthesis for achieving synthetic speech with high quality and variability based on hybrid approach","funder_award_id":"25730106","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":29,"referenced_works":["https://openalex.org/W157817982","https://openalex.org/W1514737389","https://openalex.org/W1564152904","https://openalex.org/W1600722501","https://openalex.org/W1935012542","https://openalex.org/W1963627370","https://openalex.org/W1964420823","https://openalex.org/W1965255698","https://openalex.org/W1979449467","https://openalex.org/W1984905644","https://openalex.org/W2000513720","https://openalex.org/W2049686551","https://openalex.org/W2079182758","https://openalex.org/W2093632031","https://openalex.org/W2106792148","https://openalex.org/W2111194146","https://openalex.org/W2129142580","https://openalex.org/W2156453709","https://openalex.org/W2156794882","https://openalex.org/W2405545977","https://openalex.org/W3176415168","https://openalex.org/W3196512308","https://openalex.org/W4251158933","https://openalex.org/W6633741138","https://openalex.org/W6670322988","https://openalex.org/W6676358011","https://openalex.org/W6682822505","https://openalex.org/W6798352252","https://openalex.org/W7075637324"],"related_works":["https://openalex.org/W2029561777","https://openalex.org/W1554502231","https://openalex.org/W172797710","https://openalex.org/W3165080709","https://openalex.org/W2945105049","https://openalex.org/W2626699140","https://openalex.org/W4387098302","https://openalex.org/W2948317131","https://openalex.org/W4288365855","https://openalex.org/W2111961547"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,8,26,34,101,114],"parameter":[4,36,93,134,148],"generation":[5,94],"algorithm":[6],"using":[7,41],"local":[9,31],"variance":[10,104,116],"(LV)":[11],"model":[12,39,78,89],"in":[13,132,154],"HMM-based":[14],"speech":[15,175,188],"synthesis.":[16],"In":[17,59],"the":[18,23,30,49,61,73,79,87,91,96,110,120,124,141,151,162,169,179,183],"proposed":[19,97,121,142,170],"technique,":[20],"we":[21],"define":[22],"LV":[24,52,83,88,159],"as":[25,70,72],"feature":[27],"that":[28,129,140,168],"represents":[29],"variation":[32],"of":[33,51,64,82,156,164],"spectral":[35,92,126,147,157],"sequence":[37],"and":[38,56,158],"LVs":[40,65],"HMMs.":[42],"Context-dependent":[43],"HMMs":[44],"are":[45,66],"used":[46],"to":[47,76,178],"capture":[48],"dependence":[50],"trajectories":[53,149],"on":[54],"phonetic":[55],"prosodic":[57],"contexts.":[58],"addition,":[60],"dynamic":[62,80],"features":[63],"taken":[67],"into":[68,90],"account":[69],"well":[71],"static":[74],"one":[75,181],"appropriately":[77],"characteristics":[81],"trajectories.":[84],"By":[85],"introducing":[86],"process,":[95],"technique":[98,112,122,143,153,171,185],"can":[99,144,172],"impose":[100],"more":[102],"precise":[103],"constraint":[105],"for":[106],"each":[107],"frame":[108],"than":[109,150,182],"conventional":[111,184],"with":[113],"global":[115],"(GV)":[117],"model.":[118],"Consequently,":[119],"alleviates":[123],"excessive":[125],"peak":[127],"enhancement":[128],"often":[130],"occurs":[131],"GV-based":[133,152],"generation.":[135],"Objective":[136],"evaluation":[137,166],"results":[138,163],"show":[139],"generate":[145,173],"better":[146],"terms":[155],"distortion.":[160],"Moreover,":[161],"subjective":[165],"demonstrate":[167],"synthetic":[174],"significantly":[176],"closer":[177],"original":[180],"while":[186],"maintaining":[187],"naturalness.":[189]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}