{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00216617","sets":["1164:5159:10869:10870"]},"path":["10870"],"owner":"44499","recid":"216617","title":["対話履歴の韻律情報を考慮した共感的対話音声合成"],"pubdate":{"attribute_name":"公開日","attribute_value":"2022-02-22"},"_buckets":{"deposit":"7b55419e-964f-41a0-af17-60da0c0febde"},"_deposit":{"id":"216617","pid":{"type":"depid","value":"216617","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"対話履歴の韻律情報を考慮した共感的対話音声合成","author_link":["559298","559300","559294","559292","559299","559295","559293","559297","559291","559296"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"対話履歴の韻律情報を考慮した共感的対話音声合成"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"SLP","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2022-02-22","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東京大学"},{"subitem_text_value":"東京大学"},{"subitem_text_value":"東京大学"},{"subitem_text_value":"LINE株式会社"},{"subitem_text_value":"東京大学"}]},"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/216617/files/IPSJ-SLP22140016.pdf","label":"IPSJ-SLP22140016.pdf"},"date":[{"dateType":"Available","dateValue":"2024-02-22"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP22140016.pdf","filesize":[{"value":"1.3 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":"9241eea2-a409-4302-afd3-ff829eff4c55","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2022 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"西邑, 勇人"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"齋藤, 佑樹"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"高道, 慎之介"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"橘, 健太郎"}],"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":"Yuto, Nishimura","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yuki, Saito","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shinnosuke, Takamichi","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Kentaro, Tachibana","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":"本稿では，対話履歴の言語・韻律情報を考慮し，対話相手に寄り添った発話を合成可能な共感的対話音声合成の手法を提案する．音声コミュニケーションにおいて人間は，対話の言語的・韻律的特徴から文脈を理解し，適切な韻律で対話相手に応答できる．しかし，この振る舞いをどのように計算機的に模擬し，音声合成に取り入れるかは詳細に検討されていない．提案法は，対話相手とエージェントの発話テキストと音声からクロスモーダル注意機構により推定される対話文脈埋め込みベクトルで音声合成の音響モデルを条件付けする．本研究ではさらに，対話履歴の文脈を考慮した学習を容易にするためのカリキュラム学習も検討する．実験的評価の結果より，提案法が従来法と比較して合成音声の発話自然性・対話自然性の両方を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":"2022-02-22","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"16","bibliographicVolumeNumber":"2022-SLP-140"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":216617,"updated":"2025-01-19T15:47:33.607561+00:00","links":{},"created":"2025-01-19T01:17:08.471143+00:00"}