{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00226344","sets":["1164:5064:11199:11282"]},"path":["11282"],"owner":"44499","recid":"226344","title":["オノマトペ音声を用いた効果音合成技術におけるニューラルボコーダの検討"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-06-16"},"_buckets":{"deposit":"6e3b5841-7dd9-49fd-8a54-57cfc5797459"},"_deposit":{"id":"226344","pid":{"type":"depid","value":"226344","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"オノマトペ音声を用いた効果音合成技術におけるニューラルボコーダの検討","author_link":["600722","600721"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"オノマトペ音声を用いた効果音合成技術におけるニューラルボコーダの検討"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"一般発表","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2023-06-16","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"京都産業大学大学院先端情報学研究科"},{"subitem_text_value":"京都産業大学情報理工学部"}]},"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/226344/files/IPSJ-MUS23137040.pdf","label":"IPSJ-MUS23137040.pdf"},"date":[{"dateType":"Available","dateValue":"2025-06-16"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-MUS23137040.pdf","filesize":[{"value":"12.9 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":"21"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"408529dc-9d5f-4544-a560-731d58efb81b","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"滝沢, 力"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"平井, 重行"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10438388","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":"2188-8752","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"メディア作品などの音響制作では，様々な知識や経験，スキルが要求される．望んだ音をイメージし，音韻や韻律などのニュアンスを含んだ擬音語を発話することは比較的容易であり，それらを入力として効果音に変換する生成モデルを本研究では提案している．そこでは，具体的な効果音として，様々なニュアンス表現が考えられる爆発音に焦点を当て，データセットの作成および学習，合成を試みた．その学習済モデルで，ある程度のニュアンスを考慮した合成が可能であるものの，合成音の品質向上に向けて取り組むべき課題がある．その課題のうち，今回はニューラルボコーダに注目し，iSTFTNet を用いた波形合成を試みた．本稿では，これまで利用してきた CBHG・Griffin-Lim アルゴリズムと，iSTFTNet のそれぞれで効果音を合成した結果から，その音質や波形の特徴について比較検討した内容を報告する．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告音楽情報科学（MUS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2023-06-16","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"40","bibliographicVolumeNumber":"2023-MUS-137"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":226344,"updated":"2025-01-19T12:30:26.536735+00:00","links":{},"created":"2025-01-19T01:25:47.960654+00:00"}