{"id":"https://openalex.org/W2785496868","doi":"https://doi.org/10.1109/apsipa.2017.8282285","title":"Enhanced F0 generation for GPR-based speech synthesis considering syllable-based prosodic features","display_name":"Enhanced F0 generation for GPR-based speech synthesis considering syllable-based prosodic features","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2785496868","doi":"https://doi.org/10.1109/apsipa.2017.8282285","mag":"2785496868"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2017.8282285","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282285","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-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/A5044399580","display_name":"Decha Moungsri","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":true,"raw_author_name":"Decha Moungsri","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan"],"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","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":["School of Engineering, Tokyo Institute of Technology, Yokohama, Japan"],"affiliations":[{"raw_affiliation_string":"School of Engineering, Tokyo Institute of Technology, 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":["School of Engineering, Tokyo Institute of Technology, Yokohama, Japan"],"affiliations":[{"raw_affiliation_string":"School of Engineering, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5044399580"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.21399426,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"No.","issue":null,"first_page":"1524","last_page":"1527"},"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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"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/syllable","display_name":"Syllable","score":0.7801969051361084},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6838909387588501},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.6367303729057312},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6258651614189148},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5983293652534485},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5014288425445557},{"id":"https://openalex.org/keywords/trigonometric-functions","display_name":"Trigonometric functions","score":0.4760565459728241},{"id":"https://openalex.org/keywords/pitch-contour","display_name":"Pitch contour","score":0.46349453926086426},{"id":"https://openalex.org/keywords/kriging","display_name":"Kriging","score":0.4463745355606079},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.422853946685791},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3304053544998169},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3057876229286194},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.0734383761882782}],"concepts":[{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.7801969051361084},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6838909387588501},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.6367303729057312},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6258651614189148},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5983293652534485},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5014288425445557},{"id":"https://openalex.org/C178009071","wikidata":"https://www.wikidata.org/wiki/Q93344","display_name":"Trigonometric functions","level":2,"score":0.4760565459728241},{"id":"https://openalex.org/C2777895490","wikidata":"https://www.wikidata.org/wiki/Q7198848","display_name":"Pitch contour","level":2,"score":0.46349453926086426},{"id":"https://openalex.org/C81692654","wikidata":"https://www.wikidata.org/wiki/Q225926","display_name":"Kriging","level":2,"score":0.4463745355606079},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.422853946685791},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3304053544998169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3057876229286194},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0734383761882782},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/apsipa.2017.8282285","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282285","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:00897:0004115681","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100758686","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc. 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference","raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7400000095367432,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320326788","display_name":"National Electronics and Computer Technology Center","ror":"https://ror.org/04z82ry91"},{"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":17,"referenced_works":["https://openalex.org/W113106864","https://openalex.org/W1964420823","https://openalex.org/W1971031853","https://openalex.org/W1979449467","https://openalex.org/W2029061379","https://openalex.org/W2049686551","https://openalex.org/W2100140000","https://openalex.org/W2100717696","https://openalex.org/W2109938215","https://openalex.org/W2184310502","https://openalex.org/W2402293227","https://openalex.org/W2403459093","https://openalex.org/W2407609408","https://openalex.org/W2517736208","https://openalex.org/W6713400536","https://openalex.org/W6713560526","https://openalex.org/W6714261857"],"related_works":["https://openalex.org/W1522063982","https://openalex.org/W196866866","https://openalex.org/W1890221585","https://openalex.org/W2140156791","https://openalex.org/W3093375612","https://openalex.org/W2127017784","https://openalex.org/W2360028139","https://openalex.org/W140061127","https://openalex.org/W1548055504","https://openalex.org/W2024201202"],"abstract_inverted_index":{"The":[0],"conventional":[1],"frame-level":[2,17,59],"Gaussian":[3,86],"process":[4],"regression":[5],"(GPR)-based":[6],"F0":[7,47,76,88,110],"generation":[8,111],"can":[9],"produce":[10],"natural":[11],"sounding":[12],"pitch":[13,23],"contours.":[14],"However,":[15],"a":[16,40,114],"model":[18,52],"is":[19,53],"insufficient":[20],"to":[21],"represent":[22],"patterns":[24],"in":[25,34,49,78,109],"longer":[26],"unit,":[27],"especially":[28],"for":[29,44],"syllable-":[30],"level":[31],"tone":[32],"contours":[33,89],"tonal":[35],"languages.":[36],"This":[37],"paper":[38],"proposes":[39],"multi-level":[41],"modeling":[42],"technique":[43],"improving":[45],"GPR-based":[46],"generation,":[48],"which":[50],"syllable-level":[51,63,100],"considered":[54],"as":[55,57,81],"well":[56],"the":[58,62,67,82],"model.":[60],"In":[61],"model,":[64],"we":[65],"use":[66],"discrete":[68],"cosine":[69],"transform":[70],"(DCT)":[71],"coefficients":[72],"extracted":[73],"from":[74],"log":[75],"contour":[77],"syllable":[79],"unit":[80],"output":[83],"variables":[84],"of":[85,97,104,117],"process.":[87],"are":[90],"generated":[91],"by":[92],"jointly":[93],"maximizing":[94],"predictive":[95],"distribution":[96],"frame-":[98],"and":[99],"models.":[101],"Experimental":[102],"results":[103],"objective":[105],"evaluation":[106],"show":[107],"improvement":[108],"when":[112],"using":[113],"small":[115],"amount":[116],"training":[118],"data":[119],"around":[120],"30":[121],"minutes.":[122]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}