{"links":{},"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00232558","sets":["1164:5159:11541:11549"]},"path":["11549"],"owner":"44499","recid":"232558","title":["音声エージェントの印象に合致する音声の加工強度の予測"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-02-22"},"_buckets":{"deposit":"84a32515-2c0a-4107-9335-c8c257b5cf12"},"_deposit":{"id":"232558","pid":{"type":"depid","value":"232558","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"音声エージェントの印象に合致する音声の加工強度の予測","author_link":["629785","629779","629781","629783","629786","629780","629784","629782"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"音声エージェントの印象に合致する音声の加工強度の予測"},{"subitem_title":"Prediction of Voice Processing Intensity Matching the Impression of a Voice Agent","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"SP3","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2024-02-22","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東京大学工学部"},{"subitem_text_value":"東京大学大学院工学系研究科"},{"subitem_text_value":"東京大学大学院工学系研究科"},{"subitem_text_value":"東京大学大学院工学系研究科"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Faculty of Engineering, The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Engineering, The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Engineering, The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Engineering, 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/232558/files/IPSJ-SLP24151088.pdf","label":"IPSJ-SLP24151088.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP24151088.pdf","filesize":[{"value":"2.0 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"22"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"2ae9f854-ff55-4754-922f-955f52681723","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Institute of Electronics, Information and Communication Engineers This SIG report is only available to those in membership of the SIG."}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"宮本, 蓮"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"森田, 湧大"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"齋藤, 大輔"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"峯松, 信明"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Ren, Miyamoto","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Wakuto, Morita","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Daisuke, Saito","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Nobuaki, Minematsu","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":"ロボットのような音声エージェントが人間と対話する際，その印象に合う音声を選択することがエージェントへの親しみやすさの点で重要である．本研究では，自然音声に人工感を付与する加工を施した音声を，加工強度を変えて複数用意し，Stable Diffusion で生成したサイボーグ，ロボットなどの画像に対して，どの加工強度が適切か主観的に評価する実験を行った．さらに，音声エージェントの画像に対して，得られた回答の分布を反映したラベル付けを行い，回答のばらつきも含めて学習することで，画像から適切な音声の加工強度を予測した．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"When a voice agent such as a robot interacts with a human, it is important in terms of familiarity with the agent to select a voice that fits its impression. In this study, we prepared several voices with different processing intensities, and subjectively evaluated which processing intensity was appropriate for images of cyborgs, robots, and other objects generated by Stable Diffusion. Moreover, we labeled the images of the voice agent reflecting the distribution of obtained annotations, and by learning including the variability of annotations, we predicted the appropriate degree of voice processing from the image.","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":"2024-02-22","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"88","bibliographicVolumeNumber":"2024-SLP-151"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"created":"2025-01-19T01:33:29.757457+00:00","updated":"2025-01-19T10:24:29.311203+00:00","id":232558}