{"id":"https://openalex.org/W31487335","doi":"https://doi.org/10.21437/icslp.2002-111","title":"Designing Japanese speech database covering wide range in prosody for hybrid speech synthesizer","display_name":"Designing Japanese speech database covering wide range in prosody for hybrid speech synthesizer","publication_year":2002,"publication_date":"2002-09-16","ids":{"openalex":"https://openalex.org/W31487335","doi":"https://doi.org/10.21437/icslp.2002-111","mag":"31487335"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2002-111","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://naist.repo.nii.ac.jp/record/4678/files/ICSLP_2002_2425.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005388852","display_name":"Hiromichi Kawanami","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hiromichi Kawanami","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112016059","display_name":"Tsuyoshi Masuda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsuyoshi Masuda","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5021868389","display_name":"Kiyohiro Shikano","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kiyohiro Shikano","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005388852"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4261,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.64855827,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2425","last_page":"2428"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.989799976348877,"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":0.989799976348877,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9412999749183655,"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/T12031","display_name":"Speech and dialogue systems","score":0.9387999773025513,"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/prosody","display_name":"Prosody","score":0.8418934345245361},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7232558131217957},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6595858931541443},{"id":"https://openalex.org/keywords/chinese-speech-synthesis","display_name":"Chinese speech synthesis","score":0.5362595319747925},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.532335638999939},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5140234231948853},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5015127658843994},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.428048700094223},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4194015562534332},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12637859582901}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8418934345245361},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7232558131217957},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6595858931541443},{"id":"https://openalex.org/C73411735","wikidata":"https://www.wikidata.org/wiki/Q16369","display_name":"Chinese speech synthesis","level":4,"score":0.5362595319747925},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.532335638999939},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5140234231948853},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5015127658843994},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.428048700094223},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4194015562534332},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12637859582901},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/icslp.2002-111","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01146:0005783129","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/4678","pdf_url":"https://naist.repo.nii.ac.jp/record/4678/files/ICSLP_2002_2425.pdf","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01146:0005783129","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/4678","pdf_url":"https://naist.repo.nii.ac.jp/record/4678/files/ICSLP_2002_2425.pdf","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"},"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W31487335.pdf","grobid_xml":"https://content.openalex.org/works/W31487335.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3149582125","https://openalex.org/W2349468610","https://openalex.org/W2465421051","https://openalex.org/W1984347656","https://openalex.org/W2161314515","https://openalex.org/W2181715843","https://openalex.org/W652196294","https://openalex.org/W2395605663","https://openalex.org/W2772686614","https://openalex.org/W4200068392"],"abstract_inverted_index":{"For":[0],"the":[1,82,103,110,114,121,128,131,140],"purpose":[2],"of":[3,34,58,90,109,116,130],"building":[4],"Text-to-Speech":[5],"(TTS)":[6],"system":[7,31],"that":[8],"can":[9],"generate":[10,71],"high-quality":[11],"and":[12,39,106,113,134],"wide":[13],"range":[14],"speech":[15,20,25,151],"in":[16],"prosody,":[17],"we":[18,27,84,101],"conducted":[19],"database":[21,112],"construction.":[22],"As":[23],"a":[24,29,35],"synthesizer,":[26],"use":[28],"hybrid":[30],"which":[32,61],"consists":[33],"unit":[36,144],"selection":[37,145],"module":[38],"prosody":[40,59,73,78],"modification":[41,60],"by":[42],"STRAIGHT":[43],"(vocoder":[44],"type":[45],"high":[46],"quality":[47,63],"analysis-":[48],"synthesis":[49],"method).":[50],"Our":[51],"viewpoint":[52],"is":[53,69,137],"to":[54,70,142,149],"reduce":[55],"an":[56],"amount":[57],"causes":[62],"deterioration.":[64],"In":[65,98],"other":[66],"words,":[67],"it":[68,136],"any":[72],"at":[74],"will":[75],"within":[76],"permissible":[77],"modification.":[79],"Based":[80],"on":[81,120],"aspect,":[83],"designed":[85],"9":[86],"sub-databases":[87],"those":[88],"consist":[89],"same":[91],"phonetic":[92],"balanced":[93],"texts":[94],"with":[95],"different":[96],"prosody.":[97],"this":[99],"paper,":[100],"describe":[102],"designing":[104],"policy":[105],"general":[107],"features":[108],"obtained":[111],"results":[115],"listening":[117],"tests":[118],"focused":[119],"effectiveness":[122],"about":[123],"durational":[124],"feature.":[125],"They":[126],"shows":[127],"advantage":[129],"proposed":[132],"database.":[133],"but":[135],"also":[138],"observed":[139],"necessity":[141],"change":[143],"cost":[146],"function":[147],"according":[148],"output":[150],"rate.":[152]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
