{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00210250","sets":["1164:5336:10549:10550"]},"path":["10550"],"owner":"44499","recid":"210250","title":["メロディを対象とした生成Deep Learningモデルの比較"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-03-09"},"_buckets":{"deposit":"e320ec99-53a8-4ec8-b38a-5bb89da4224a"},"_deposit":{"id":"210250","pid":{"type":"depid","value":"210250","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"メロディを対象とした生成Deep Learningモデルの比較","author_link":["531768"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"メロディを対象とした生成Deep Learningモデルの比較"}]},"item_type_id":"4","publish_date":"2021-03-09","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"駒澤大学"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Komazawa University","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/210250/files/IPSJ-EC21059015.pdf","label":"IPSJ-EC21059015.pdf"},"date":[{"dateType":"Available","dateValue":"2023-03-09"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-EC21059015.pdf","filesize":[{"value":"587.4 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"40"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"6f02f9a5-2708-4a82-82b1-9835e9e5bd25","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2021 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"平井, 辰典"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA12049625","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":"2188-8914","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"様々なメディア分野で生成 Deep Learning モデルが提案されており，その生成品質は年々向上している．音楽生成分野における生成モデルの発展についても，「音楽理論を逸脱するような音の生成例が減った」，「文脈を考慮したメロディを生成できている」といった品質の向上は認められると言える．しかし，こと音楽に関しては「より品質の良い生成結果である」ということを評価することが簡単ではない．本稿では，各種生成 Deep Learning モデルの実装を通じて，出力結果の品質を評価するのではなくそれぞれの特徴について客観的な比較を行う．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"12","bibliographic_titles":[{"bibliographic_title":"研究報告エンタテインメントコンピューティング（EC）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2021-03-09","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"15","bibliographicVolumeNumber":"2021-EC-59"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"updated":"2025-01-19T18:12:56.662799+00:00","created":"2025-01-19T01:11:30.447232+00:00","links":{},"id":210250}