{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00213244","sets":["1164:5159:10515:10722"]},"path":["10722"],"owner":"44499","recid":"213244","title":["韻律情報で条件付けされた非自己回帰型End-to-End日本語音声合成の検討"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-10-12"},"_buckets":{"deposit":"8dfd7ce6-cbda-4cac-a270-7d5bec8f8154"},"_deposit":{"id":"213244","pid":{"type":"depid","value":"213244","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"韻律情報で条件付けされた非自己回帰型End-to-End日本語音声合成の検討","author_link":["545329","545331","545327","545328","545332","545330"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"韻律情報で条件付けされた非自己回帰型End-to-End日本語音声合成の検討"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"H/SP/SLP","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2021-10-12","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東京大学大学院情報理工学系研究科"},{"subitem_text_value":"東京大学大学院情報理工学系研究科"},{"subitem_text_value":"東京大学大学院情報理工学系研究科"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Information Science and Technology, The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Science and Technology, The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Science and Technology, The University of Tokyo","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/213244/files/IPSJ-SLP21138016.pdf","label":"IPSJ-SLP21138016.pdf"},"date":[{"dateType":"Available","dateValue":"2023-10-12"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP21138016.pdf","filesize":[{"value":"1.4 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"22"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"9d930ff5-5215-4545-9d15-4e8e6469b998","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2021 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"藤井, 一貴"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"齋藤, 佑樹"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"猿渡, 洋"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Kazuki, Fujii","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yuki, Saito","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hiroshi, Saruwatari","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10442647","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8663","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"日本語音声合成において，合成音声のアクセントは合成音声の品質に大きく寄与するだけでなく，正確な情報伝達を行う上で重要な情報である．しかし，音素や文字などの生テキストに近い情報から音声を予測する End-to-End 日本語音声合成では，合成音声のアクセント誤りが頻出する．提案手法では非自己回帰型 End-to-End 音声合成モデルの代表である FastSpeech2 に入力する音素記号に，テキスト解析により得られた韻律情報を取り込むことで，アクセント誤りの改善を目指す．また，韻律情報を抽出する際のテキスト解析で用いる辞書の影響も調査する．実験的評価の結果より，提案手法が合成音声の韻律予測精度と自然性を有意に改善させることを示す．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告音声言語情報処理（SLP）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2021-10-12","bibliographicIssueDateType":"Issued"},"bibliographicVolumeNumber":"2021-SLP-138"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":213244,"updated":"2025-01-19T17:13:37.564792+00:00","links":{},"created":"2025-01-19T01:14:07.865417+00:00"}