{"links":{},"id":236050,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00236050","sets":["6504:11678:11689"]},"path":["11689"],"owner":"44499","recid":"236050","title":["End-to-Endモデルに基づく混合感情の音声合成に関する検討"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-03-01"},"_buckets":{"deposit":"d8d5cf6e-0a85-426c-a155-c80dd04ddc91"},"_deposit":{"id":"236050","pid":{"type":"depid","value":"236050","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"End-to-Endモデルに基づく混合感情の音声合成に関する検討","author_link":["645103","645102"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"End-to-Endモデルに基づく混合感情の音声合成に関する検討"}]},"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":"2024-03-01","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":"山形大"},{"subitem_text_value":"山形大"}]},"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/236050/files/IPSJ-Z86-5R-06.pdf","label":"IPSJ-Z86-5R-06.pdf"},"date":[{"dateType":"Available","dateValue":"2024-07-03"}],"format":"application/pdf","filename":"IPSJ-Z86-5R-06.pdf","filesize":[{"value":"1.3 MB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"966c2bb2-938e-4041-8f2d-eb4127cd1af0","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"TIANYI, LI"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"小坂, 哲夫"}],"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":"　最近、VITSなどE2EのTTSモデルが提案され、従来の2段階モデルよりも優れた性能を示している。この進歩により、より表現豊かなTTSの研究が進展し、その中で混合感情のTTSが注目されている。先行研究では、エンコーダデコーダベースの混合感情TTSモデルが提案されたが、E2Eモデルの検討は十分になされていない。　本研究では、VITSをベースに、線形結合を用いた混合感情の音声合成と主観評価実験を行った。一方、音声感情認識から抽出した感情ベクトルの汎用性についても検証した。その結果、感情ベクトルは高い汎用性を持ち、線形結合により合成した混合感情の音声は人間の直観に類似していることが確認された。","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"416","bibliographic_titles":[{"bibliographic_title":"第86回全国大会講演論文集"}],"bibliographicPageStart":"415","bibliographicIssueDates":{"bibliographicIssueDate":"2024-03-01","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2024"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"created":"2025-01-19T01:37:53.506000+00:00","updated":"2025-01-19T09:24:53.791912+00:00"}