{"links":{},"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00220978","sets":["6504:11035:11043"]},"path":["11043"],"owner":"44499","recid":"220978","title":["波形接続型音声合成における歌唱のピッチ変化予測LSTMモデル"],"pubdate":{"attribute_name":"公開日","attribute_value":"2022-02-17"},"_buckets":{"deposit":"7d433b6e-9537-4813-b324-e92ec232a2f2"},"_deposit":{"id":"220978","pid":{"type":"depid","value":"220978","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"波形接続型音声合成における歌唱のピッチ変化予測LSTMモデル","author_link":["578305","578306","578307"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"波形接続型音声合成における歌唱のピッチ変化予測LSTMモデル"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"人工知能と認知科学","subitem_subject_scheme":"Other"}]},"item_type_id":"22","publish_date":"2022-02-17","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_22_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"はこだて未来大"},{"subitem_text_value":"はこだて未来大"},{"subitem_text_value":"はこだて未来大"}]},"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/220978/files/IPSJ-Z84-1T-01.pdf","label":"IPSJ-Z84-1T-01.pdf"},"date":[{"dateType":"Available","dateValue":"2022-10-22"}],"format":"application/pdf","filename":"IPSJ-Z84-1T-01.pdf","filesize":[{"value":"271.6 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"1a7f9cfa-8f38-45f6-927c-dec536a384d6","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2022 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"田中, 瑞穂"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"竹川, 佳成"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"平田, 圭二"}],"nameIdentifiers":[{}]}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_5794","resourcetype":"conference paper"}]},"item_22_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00349328","subitem_source_identifier_type":"NCID"}]},"item_22_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"本研究では，波形接続型音声合成を用いた歌唱合成システムの歌唱技術を学習することで，ユーザによるパラメータ制御を支援することを目的とする．近年，統計的音声合成によって人間の歌唱を模倣する研究が注目されている．しかし，この手法では，高速歌唱などの人間歌唱が困難である合成音声特有の歌唱技術に対応できない．そこで，本研究では，手動で調節した歌唱合成システムの楽譜のテキストデータをLSTMで学習した．この学習したLSTMを用いて，未知の楽譜のパラメータを予測及び生成した．なお，学習するパラメータは，ポルタメントやヴィブラートなどピッチを変化させて抑揚をつける機能に焦点を当てている．","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"474","bibliographic_titles":[{"bibliographic_title":"第84回全国大会講演論文集"}],"bibliographicPageStart":"473","bibliographicIssueDates":{"bibliographicIssueDate":"2022-02-17","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2022"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"created":"2025-01-19T01:20:59.825619+00:00","updated":"2025-01-19T14:20:53.055616+00:00","id":220978}