{"updated":"2025-01-19T13:09:16.278668+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00224430","sets":["1164:5159:11151:11203"]},"path":["11203"],"owner":"44499","recid":"224430","title":["Visual onoma-to-wave：画像オノマトペと音源画像を利用した環境音合成の提案"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-02-21"},"_buckets":{"deposit":"94d68b34-8bf3-44dd-a274-3b7a7c439e8b"},"_deposit":{"id":"224430","pid":{"type":"depid","value":"224430","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Visual onoma-to-wave：画像オノマトペと音源画像を利用した環境音合成の提案","author_link":["591816","591820","591822","591811","591812","591813","591815","591821","591819","591817","591818","591814"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Visual onoma-to-wave：画像オノマトペと音源画像を利用した環境音合成の提案"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"SP-EA:音響・モデル","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2023-02-21","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"徳山工業高等専門学校"},{"subitem_text_value":"東京大学"},{"subitem_text_value":"同志社大学"},{"subitem_text_value":"立命館大学"},{"subitem_text_value":"東京大学"},{"subitem_text_value":"東京大学"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"National Institute of Technology, Tokuyama College","subitem_text_language":"en"},{"subitem_text_value":"The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"Doshisha University","subitem_text_language":"en"},{"subitem_text_value":"Ritsumeikan University","subitem_text_language":"en"},{"subitem_text_value":"The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"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/224430/files/IPSJ-SLP23146033.pdf","label":"IPSJ-SLP23146033.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP23146033.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":"f3489edb-54a6-4eb1-82e3-44892ff4a6d6","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 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":"大中, 緋慧"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"高道, 慎之介"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"井本, 桂右"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"岡本, 悠希"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"藤井, 一貴"}],"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":"Hien, Ohnaka","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shinnnosuke, Takamichi","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Keisuke, Imoto","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yuki, Okamoto","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Kazuki, Fujii","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":"オノマトペとは，音の構造を模倣する文字表現，つまり音の文字表現である．この観点から，所望のオノマトペから環境音を合成する Onoma-to-wave が提案されている．他方，オノマトペには漫画や広告，バーチャルリアリティにおける音の視覚的表現（画像オノマトペ）がある．画像オノマトペには，画像の伸縮などの文字だけでは表現できない表現が含まれており，この表現を用いることでより多様な音の合成が期待できる．そこで本研究は，画像オノマトペから環境音を合成する Visual onoma-to-wave を提案する．本手法は，画像オノマトペに含まれる視覚表現のみならず，環境音源の視覚表現（音源画像）を補助情報として，環境音を合成する．また本論文では，オノマトペの反復表現に着目したデータ拡張手法を提案し，より多様な環境音合成を可能にする．実験評価の結果から，画像オノマトペと音源画像から多様な環境音を合成できることが示す．\n","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":"2023-02-21","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"33","bibliographicVolumeNumber":"2023-SLP-146"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"created":"2025-01-19T01:24:01.224646+00:00","id":224430,"links":{}}