{"id":"https://openalex.org/W2029061379","doi":"https://doi.org/10.1109/icassp.2014.6854319","title":"Parametric speech synthesis based on Gaussian process regression using global variance and hyperparameter optimization","display_name":"Parametric speech synthesis based on Gaussian process regression using global variance and hyperparameter optimization","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2029061379","doi":"https://doi.org/10.1109/icassp.2014.6854319","mag":"2029061379"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100668124/ATD100000413/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024181978","display_name":"Tomoki Koriyama","orcid":"https://orcid.org/0000-0002-8347-5604"},"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":"Tomoki Koriyama","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology","Interdisciplinary Graduate School of Sci. and Eng., Tokyo Inst. of Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Interdisciplinary Graduate School of Sci. and Eng., Tokyo Inst. of Tech","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103144936","display_name":"Takashi Nose","orcid":"https://orcid.org/0000-0001-5403-0019"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Nose","raw_affiliation_strings":["Graduate School of Engineering, Tohoku University","Graduate School of Engineering / Tohoku University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Tohoku University","institution_ids":["https://openalex.org/I201537933"]},{"raw_affiliation_string":"Graduate School of Engineering / Tohoku University","institution_ids":["https://openalex.org/I201537933"]}]},{"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":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology","Interdisciplinary Graduate School of Sci. and Eng., Tokyo Inst. of Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Interdisciplinary Graduate School of Sci. and Eng., Tokyo Inst. of Tech","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4474,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84041175,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3834","last_page":"3838"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9984999895095825,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9984999895095825,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9966999888420105,"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":0.9843000173568726,"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/hyperparameter","display_name":"Hyperparameter","score":0.9279264211654663},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.6900355219841003},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6584942936897278},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.616989016532898},{"id":"https://openalex.org/keywords/kriging","display_name":"Kriging","score":0.6054450273513794},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5864386558532715},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49841856956481934},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.47957462072372437},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4661978781223297},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.43741464614868164},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43207088112831116},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.428668737411499},{"id":"https://openalex.org/keywords/kernel-smoother","display_name":"Kernel smoother","score":0.4159887731075287},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39777278900146484},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.3517773747444153},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33922260999679565},{"id":"https://openalex.org/keywords/kernel-method","display_name":"Kernel method","score":0.3020329177379608},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2634938955307007},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.20318779349327087},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.16532132029533386},{"id":"https://openalex.org/keywords/radial-basis-function-kernel","display_name":"Radial basis function kernel","score":0.079190194606781}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.9279264211654663},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.6900355219841003},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6584942936897278},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.616989016532898},{"id":"https://openalex.org/C81692654","wikidata":"https://www.wikidata.org/wiki/Q225926","display_name":"Kriging","level":2,"score":0.6054450273513794},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5864386558532715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49841856956481934},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.47957462072372437},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4661978781223297},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.43741464614868164},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43207088112831116},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.428668737411499},{"id":"https://openalex.org/C27406209","wikidata":"https://www.wikidata.org/wiki/Q6394203","display_name":"Kernel smoother","level":5,"score":0.4159887731075287},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39777278900146484},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3517773747444153},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33922260999679565},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.3020329177379608},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2634938955307007},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.20318779349327087},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.16532132029533386},{"id":"https://openalex.org/C75866337","wikidata":"https://www.wikidata.org/wiki/Q7280263","display_name":"Radial basis function kernel","level":4,"score":0.079190194606781},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"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":2,"locations":[{"id":"doi:10.1109/icassp.2014.6854319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50233335","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100668124","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100668124/ATD100000413/","source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"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 Paper"}],"best_oa_location":{"id":"pmh:oai:t2r2.star.titech.ac.jp:50233335","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100668124","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100668124/ATD100000413/","source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"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 Paper"},"sustainable_development_goals":[],"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/G1897481696","display_name":"Research on speech synthesis using non-parametric modeling based on Gaussian process regression","funder_award_id":"25540065","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2029061379.pdf","grobid_xml":"https://content.openalex.org/works/W2029061379.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1531312258","https://openalex.org/W1580216809","https://openalex.org/W1600722501","https://openalex.org/W1746819321","https://openalex.org/W1963627370","https://openalex.org/W1965255698","https://openalex.org/W1971031853","https://openalex.org/W2000513720","https://openalex.org/W2049686551","https://openalex.org/W2076638338","https://openalex.org/W2102003408","https://openalex.org/W2111194146","https://openalex.org/W2129142580","https://openalex.org/W2403459093","https://openalex.org/W2432517183","https://openalex.org/W2981264952","https://openalex.org/W4211049957","https://openalex.org/W4301420498","https://openalex.org/W6631924718","https://openalex.org/W6634689341","https://openalex.org/W6675380101","https://openalex.org/W6676358011","https://openalex.org/W6713560526"],"related_works":["https://openalex.org/W2141609920","https://openalex.org/W2912851808","https://openalex.org/W4294619368","https://openalex.org/W4380558509","https://openalex.org/W4286748465","https://openalex.org/W566010457","https://openalex.org/W2600092203","https://openalex.org/W3118984993","https://openalex.org/W2144336328","https://openalex.org/W3196933554"],"abstract_inverted_index":{"This":[0],"paper":[1],"examines":[2],"two":[3],"issues":[4,35],"of":[5,34],"a":[6,32],"statistical":[7],"speech":[8,18],"synthesis":[9,19],"approach":[10],"based":[11],"Gaussian":[12],"process":[13],"(GP)":[14],"regression.":[15],"Although":[16],"GP-based":[17],"can":[20],"give":[21],"higher":[22],"performance":[23,91],"in":[24,56,64,92],"generating":[25],"spectral":[26,93],"parameters":[27],"than":[28],"the":[29,52,90],"HMM-based":[30],"one,":[31],"number":[33],"still":[36],"remain.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41,69],"incorporate":[42],"global":[43],"variance":[44],"(GV)":[45],"feature":[46,94],"to":[47,58],"overcome":[48],"over-smoothing":[49],"problem":[50],"into":[51],"parameter":[53],"generation.":[54,95],"Furthermore,":[55],"order":[57],"utilize":[59],"an":[60,71],"appropriate":[61],"kernel":[62,73],"function":[63],"accordance":[65],"with":[66],"actual":[67],"data,":[68],"propose":[70],"EM-based":[72],"hyperparameter":[74,87],"optimization":[75],"technique.":[76],"Objective":[77],"and":[78,86],"subjective":[79],"evaluation":[80],"results":[81],"show":[82],"that":[83],"using":[84],"GV":[85],"estimation":[88],"enhanced":[89]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}