{"id":205301,"updated":"2025-01-19T19:54:20.203324+00:00","links":{},"created":"2025-01-19T01:07:27.875433+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00205301","sets":["6504:10247:10254"]},"path":["10254"],"owner":"6748","recid":"205301","title":["深層クラスタリングを用いた任意楽器パートの自動採譜"],"pubdate":{"attribute_name":"公開日","attribute_value":"2020-02-20"},"_buckets":{"deposit":"36d59fef-86b1-4bc2-a6d8-801ab081cd4b"},"_deposit":{"id":"205301","pid":{"type":"depid","value":"205301","revision_id":0},"owners":[6748],"status":"published","created_by":6748},"item_title":"深層クラスタリングを用いた任意楽器パートの自動採譜","author_link":["509350","509347","509351","509349","509348"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"深層クラスタリングを用いた任意楽器パートの自動採譜"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"人工知能と認知科学","subitem_subject_scheme":"Other"}]},"item_type_id":"22","publish_date":"2020-02-20","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_22_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"早大"},{"subitem_text_value":"早大"},{"subitem_text_value":"京大"},{"subitem_text_value":"京大"},{"subitem_text_value":"早大"}]},"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/205301/files/IPSJ-Z82-5S-03.pdf","label":"IPSJ-Z82-5S-03.pdf"},"date":[{"dateType":"Available","dateValue":"2020-06-19"}],"format":"application/pdf","filename":"IPSJ-Z82-5S-03.pdf","filesize":[{"value":"551.5 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"4f0f7011-1e3e-4118-a65a-98a25bfc1821","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2020 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"田中, 啓太郎"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"中塚, 貴之"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"錦見, 亮"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"吉井, 和佳"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"森島, 繁生"}],"nameIdentifiers":[{}]}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_5794","resourcetype":"conference paper"}]},"item_22_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00349328","subitem_source_identifier_type":"NCID"}]},"item_22_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"本研究では、任意の複数楽器で演奏された音楽音響信号に対して、各パートを自動採譜する手法を提案する。近年、深層学習によって識別性能や表現学習が大幅に向上したことによって、複数楽器の自動採譜が提案されるようになった。しかし多くの場合、採譜したい楽器について教師データを用意する必要があり、多様な楽器や音源全てに対し事前に学習することは現実的ではない。任意の音楽音響信号に対する採譜を行うため、楽器ラベルによる分類ではなくクラスタリングを用いることで、教師なし学習を行う枠組みを提案する。ネットワーク全体の最適化を通じて音源分離とパート譜採譜のマルチタスク学習を行うことで、各パートの採譜を実現する。","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"366","bibliographic_titles":[{"bibliographic_title":"第82回全国大会講演論文集"}],"bibliographicPageStart":"365","bibliographicIssueDates":{"bibliographicIssueDate":"2020-02-20","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2020"}]},"relation_version_is_last":true,"weko_creator_id":"6748"}}