{"created":"2026-03-11T07:08:23.175431+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:02008671","sets":["1164:4619:1767693301673:1772440944186"]},"path":["1772440944186"],"owner":"80578","recid":"2008671","title":["テキスト条件付き音楽生成モデルを用いたゲームの場面に応じたBGMの生成"],"pubdate":{"attribute_name":"PubDate","attribute_value":"2026-03-17"},"_buckets":{"deposit":"039fdf6a-f718-45f7-8e00-f7a8653a3b96"},"_deposit":{"id":"2008671","pid":{"type":"depid","value":"2008671","revision_id":0},"owners":[80578],"status":"published","created_by":80578},"item_title":"テキスト条件付き音楽生成モデルを用いたゲームの場面に応じたBGMの生成","author_link":[],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"テキスト条件付き音楽生成モデルを用いたゲームの場面に応じたBGMの生成","subitem_title_language":"ja"},{"subitem_title":"Background Music Generation depending on Game Situation using Text-to-Music model","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"PRMU","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2026-03-17","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東洋大学大学院総合情報研究科総合情報学専攻"},{"subitem_text_value":"東洋大学大学総合情報学部"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Toyo University Graduate School of Information Science, Department of Information Science","subitem_text_language":"en"},{"subitem_text_value":"Toyo University of Information Science","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/2008671/files/IPSJ-CVIM26245005.pdf","label":"IPSJ-CVIM26245005.pdf"},"date":[{"dateType":"Available","dateValue":"9999-01-01"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CVIM26245005.pdf","filesize":[{"value":"1.3 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"20"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"c8077cf0-6f77-42e2-8cf6-690c8c3f818f","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2026 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":"藤澤,透冴"}]},{"creatorNames":[{"creatorName":"村上,真"}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Tougo Fujisawa","creatorNameLang":"en"}]},{"creatorNames":[{"creatorName":"Makoto Murakami","creatorNameLang":"en"}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11131797","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":"2188-8701","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"本研究の目的は，個人でゲームを制作している開発者にとって負担となるゲームBGMを簡単に制作できるシステムを構築することである．テキストを入力すれば楽曲を生成することができるテキスト条件付き音楽生成モデルでは，曲のジャンルやムードや楽器構成といった音楽的特徴を記述したテキストを入力する必要があるが，専門的な音楽知識を有しないゲーム開発者がそういった内容のテキストを記述することは容易ではない．一方，ゲーム映像の内容を自然言語で記述することは容易であると考え，本研究ではゲームの場面情報を記述したテキストからゲームBGMの生成を行う．具体的には，場面情報を記述したテキストを大規模言語モデルにより音楽的特徴を記述したテキストに変換し，そのテキストをテキスト条件付き楽曲生成モデルであるMusicGenに入力することでゲームBGMを生成する．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"The objective of this study is to develop a system that enables independent game developers to easily create background music (BGM), which is often a significant burden in solo game production. Text-to-Music models can generate music from textual input; however, they require descriptions of musical attributes such as genre, mood, and instrumentation. For game developers without specialized musical knowledge, it is not easy to compose such musically detailed descriptions. On the other hand, it is relatively easy to describe the content of game scenes in natural language. Therefore, this study proposes a method for generating game BGM from text that describes scene information. Specifically, text describing the game scene is first transformed into text describing musical attributes using LLM. The resulting text is then provided as input to MusicGen, a Text-to-Music model, in order to generate the game BGM.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"5","bibliographic_titles":[{"bibliographic_title":"研究報告コンピュータビジョンとイメージメディア（CVIM）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2026-03-17","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"5","bibliographicVolumeNumber":"2026-CVIM-245"}]},"relation_version_is_last":true,"weko_creator_id":"80578"},"id":2008671,"updated":"2026-03-11T07:08:27.435164+00:00","links":{}}