{"id":"https://openalex.org/W1971031853","doi":"https://doi.org/10.1109/icassp.2013.6639224","title":"Frame-level acoustic modeling based on Gaussian process regression for statistical nonparametric speech synthesis","display_name":"Frame-level acoustic modeling based on Gaussian process regression for statistical nonparametric speech synthesis","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W1971031853","doi":"https://doi.org/10.1109/icassp.2013.6639224","mag":"1971031853"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639224","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/CTT100657345/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, Yokohama, Japan","Interdiscipl. Grad. Sch. of Sci. & Eng., Tokyo Inst. of Technol., Yokohama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Interdiscipl. Grad. Sch. of Sci. & Eng., Tokyo Inst. of Technol., Yokohama, Japan","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/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":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","Interdiscipl. Grad. Sch. of Sci. & Eng., Tokyo Inst. of Technol., Yokohama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Interdiscipl. Grad. Sch. of Sci. & Eng., 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":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","Interdiscipl. Grad. Sch. of Sci. & Eng., Tokyo Inst. of Technol., Yokohama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Interdiscipl. Grad. Sch. of Sci. & Eng., 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":0.4576,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.57636247,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"87","issue":null,"first_page":"8007","last_page":"8011"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987000226974487,"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":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.7460862398147583},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5698007345199585},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5577570796012878},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.5415970683097839},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5301234126091003},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.48143240809440613},{"id":"https://openalex.org/keywords/kernel-regression","display_name":"Kernel regression","score":0.48072078824043274},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4618152379989624},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4547317922115326},{"id":"https://openalex.org/keywords/nonparametric-regression","display_name":"Nonparametric regression","score":0.45259758830070496},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4438195824623108},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4219474494457245},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4216950833797455},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.361357718706131},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34679293632507324},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.3459588885307312},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.2842472195625305},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.28369611501693726},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19935807585716248},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15246722102165222}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7460862398147583},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5698007345199585},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5577570796012878},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.5415970683097839},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5301234126091003},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.48143240809440613},{"id":"https://openalex.org/C200695384","wikidata":"https://www.wikidata.org/wiki/Q1739319","display_name":"Kernel regression","level":3,"score":0.48072078824043274},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4618152379989624},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4547317922115326},{"id":"https://openalex.org/C74127309","wikidata":"https://www.wikidata.org/wiki/Q3455886","display_name":"Nonparametric regression","level":3,"score":0.45259758830070496},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4438195824623108},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4219474494457245},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4216950833797455},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.361357718706131},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34679293632507324},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.3459588885307312},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.2842472195625305},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28369611501693726},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19935807585716248},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15246722102165222},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/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":2,"locations":[{"id":"doi:10.1109/icassp.2013.6639224","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50208122","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100657345","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100657345/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:50208122","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100657345","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100657345/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":[{"id":"https://metadata.un.org/sdg/16","score":0.800000011920929,"display_name":"Peace, Justice and strong institutions"}],"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/G2575318995","display_name":"A study on speech diversification techniques based on corpus design for advanced humanoid speech synthesis","funder_award_id":"23700195","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1971031853.pdf","grobid_xml":"https://content.openalex.org/works/W1971031853.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1510073064","https://openalex.org/W1531312258","https://openalex.org/W1600722501","https://openalex.org/W2049686551","https://openalex.org/W2109915598","https://openalex.org/W2129142580","https://openalex.org/W2165255420","https://openalex.org/W2179117922","https://openalex.org/W3142087749","https://openalex.org/W4211049957","https://openalex.org/W6631924718","https://openalex.org/W7075637324"],"related_works":["https://openalex.org/W2213164457","https://openalex.org/W2151924912","https://openalex.org/W1977532368","https://openalex.org/W1985258161","https://openalex.org/W2057032881","https://openalex.org/W2697282650","https://openalex.org/W3121786440","https://openalex.org/W3124373708","https://openalex.org/W2922896031","https://openalex.org/W1808447900"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,64,71,80,100],"new":[4],"approach":[5,90],"to":[6,16],"text-to-speech":[7],"based":[8],"on":[9],"Gaussian":[10,24],"processes":[11],"which":[12],"are":[13],"widely":[14],"used":[15,98],"perform":[17],"non-parametric":[18],"Bayesian":[19],"regression":[20,26],"and":[21,51,53],"classification.":[22],"The":[23,42],"process":[25],"model":[27],"is":[28,68],"designed":[29],"for":[30],"the":[31,38,49,85,88],"prediction":[32],"of":[33,74,87],"frame-level":[34],"acoustic":[35],"features":[36,94],"from":[37,58],"corresponding":[39],"frame":[40,43,65],"information.":[41,60],"information":[44,56],"includes":[45],"relative":[46],"position":[47],"in":[48,99],"phone":[50],"preceding":[52],"succeeding":[54],"phoneme":[55],"obtained":[57],"linguistic":[59],"In":[61],"this":[62],"paper,":[63],"context":[66],"kernel":[67],"proposed":[69,89],"as":[70],"similarity":[72],"measure":[73],"respective":[75],"frames.":[76],"Experimental":[77],"results":[78],"using":[79],"small":[81],"data":[82],"set":[83],"show":[84],"potential":[86],"without":[91],"state-dependent":[92],"dynamic":[93],"or":[95],"decision-tree":[96],"clustering":[97],"conventional":[101],"HMM-based":[102],"approach.":[103]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}