{"id":"https://openalex.org/W2159464136","doi":"https://doi.org/10.1109/mlsp.2011.6064596","title":"Representing fundamental frequency contours generated by HMM-based speech synthesis using generation process model","display_name":"Representing fundamental frequency contours generated by HMM-based speech synthesis using generation process model","publication_year":2011,"publication_date":"2011-09-01","ids":{"openalex":"https://openalex.org/W2159464136","doi":"https://doi.org/10.1109/mlsp.2011.6064596","mag":"2159464136"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp.2011.6064596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2011.6064596","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Workshop on Machine Learning for Signal Processing","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/A5108197272","display_name":"Keikichi Hirose","orcid":null},"institutions":[{"id":"https://openalex.org/I153327471","display_name":"Bunkyo University","ror":"https://ror.org/053h75930","country_code":"JP","type":"education","lineage":["https://openalex.org/I153327471"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keikichi Hirose","raw_affiliation_strings":["Department of Information and Communication Engineering, University of Tokyo, Bunkyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Communication Engineering, University of Tokyo, Bunkyo, Tokyo, Japan","institution_ids":["https://openalex.org/I153327471","https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112437619","display_name":"Tatsuya Matsuda","orcid":null},"institutions":[{"id":"https://openalex.org/I153327471","display_name":"Bunkyo University","ror":"https://ror.org/053h75930","country_code":"JP","type":"education","lineage":["https://openalex.org/I153327471"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Matsuda","raw_affiliation_strings":["Department of Information and Communication Engineering, University of Tokyo, Bunkyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Communication Engineering, University of Tokyo, Bunkyo, Tokyo, Japan","institution_ids":["https://openalex.org/I153327471","https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103995821","display_name":"Hiroya Hashimoto","orcid":null},"institutions":[{"id":"https://openalex.org/I153327471","display_name":"Bunkyo University","ror":"https://ror.org/053h75930","country_code":"JP","type":"education","lineage":["https://openalex.org/I153327471"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroya Hashimoto","raw_affiliation_strings":["Department of Information and Communication Engineering, University of Tokyo, Bunkyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Communication Engineering, University of Tokyo, Bunkyo, Tokyo, Japan","institution_ids":["https://openalex.org/I153327471","https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041213266","display_name":"Nobuaki Minematsu","orcid":"https://orcid.org/0000-0002-8778-9555"},"institutions":[{"id":"https://openalex.org/I153327471","display_name":"Bunkyo University","ror":"https://ror.org/053h75930","country_code":"JP","type":"education","lineage":["https://openalex.org/I153327471"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobuaki Minematsu","raw_affiliation_strings":["Department of Information and Communication Engineering, University of Tokyo, Bunkyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Communication Engineering, University of Tokyo, Bunkyo, Tokyo, Japan","institution_ids":["https://openalex.org/I153327471","https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"50","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9857000112533569,"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":0.9621999859809875,"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/speech-synthesis","display_name":"Speech synthesis","score":0.7820494771003723},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.667214572429657},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6671339273452759},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5417765378952026},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5024120807647705},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5008761882781982},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47966957092285156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47702571749687195},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.47042155265808105},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.46298539638519287},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4498351216316223},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.09026870131492615}],"concepts":[{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7820494771003723},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.667214572429657},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6671339273452759},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5417765378952026},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5024120807647705},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5008761882781982},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47966957092285156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47702571749687195},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.47042155265808105},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.46298539638519287},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4498351216316223},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.09026870131492615},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp.2011.6064596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2011.6064596","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Workshop on Machine Learning for Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W26451783","https://openalex.org/W198545297","https://openalex.org/W386798966","https://openalex.org/W1514737389","https://openalex.org/W1981450667","https://openalex.org/W2034277951","https://openalex.org/W2071399124","https://openalex.org/W2138384405","https://openalex.org/W2151103935","https://openalex.org/W2166823384","https://openalex.org/W4390926479","https://openalex.org/W6613242975","https://openalex.org/W6668594742","https://openalex.org/W6684457288","https://openalex.org/W6860918170"],"related_works":["https://openalex.org/W2317723112","https://openalex.org/W2475724061","https://openalex.org/W2773393136","https://openalex.org/W2174706483","https://openalex.org/W2997121352","https://openalex.org/W419536403","https://openalex.org/W2506280730","https://openalex.org/W4237969969","https://openalex.org/W175280642","https://openalex.org/W2688184458"],"abstract_inverted_index":{"Frame-by-frame":[0],"representation":[1],"is":[2,48,104],"not":[3],"appropriate":[4],"for":[5],"prosodic":[6],"features,":[7],"which":[8],"are":[9],"tightly":[10],"related":[11],"to":[12,50,67,106,112],"speech":[13,44,88,115,142],"units":[14],"spreading":[15],"a":[16,61,96],"wide":[17],"time":[18],"span,":[19],"such":[20],"as":[21,110,150],"words,":[22],"phrases":[23],"and":[24,75,129,144],"so":[25],"on.":[26],"This":[27],"causes":[28],"an":[29,138],"inherit":[30],"problem":[31],"in":[32,57],"fundamental":[33],"frequency":[34],"(F":[35],"<inf":[36,53,81],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[37,54,82],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">0</inf>":[38,55,83],")":[39],"contour":[40],"generation":[41,62,121],"by":[42,65],"HMM-based":[43,87,114],"synthesis.":[45],"A":[46],"method":[47,103,136],"developed":[49],"modify":[51],"F":[52,80],"contours":[56],"the":[58,93,102,113,120,135,158],"framework":[59],"of":[60,70],"process":[63,122],"model":[64,123],"referring":[66],"linguistic":[68,130],"information":[69,148],"input":[71],"text":[72],"(word":[73],"boundary":[74],"accent":[76],"type).":[77],"It":[78],"takes":[79],"variances":[84],"obtained":[85],"through":[86,156],"synthesis":[89,116],"into":[90],"account":[91],"during":[92],"process.":[94],"Through":[95],"listening":[97],"experiment":[98],"on":[99,117],"synthetic":[100],"speech,":[101],"proved":[105],"generate":[107],"better":[108],"quality":[109],"compared":[111],"average.":[118],"Since":[119],"can":[124,152],"clearly":[125],"relate":[126],"its":[127],"commands":[128],"(and":[131],"para-/non-":[132],"linguistic)":[133],"information,":[134],"has":[137],"additional":[139],"advantage;":[140],"changing":[141],"styles,":[143],"/or":[145],"adding":[146],"further":[147],"(such":[149],"emphasis)":[151],"be":[153],"easily":[154],"done":[155],"manipulating":[157],"commands.":[159]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}