{"created":"2025-01-19T01:29:31.442414+00:00","updated":"2025-01-19T11:19:26.193572+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00230016","sets":["6504:11436:11440"]},"path":["11440"],"owner":"44499","recid":"230016","title":["視聴覚自己教師あり学習に基づく音響イベント検出"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-02-16"},"_buckets":{"deposit":"c7809b5a-2115-410d-b5ee-7a62d250096b"},"_deposit":{"id":"230016","pid":{"type":"depid","value":"230016","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"視聴覚自己教師あり学習に基づく音響イベント検出","author_link":["618826","618829","618827","618828"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"視聴覚自己教師あり学習に基づく音響イベント検出"}]},"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":"2023-02-16","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":"筑波大"},{"subitem_text_value":"産総研"},{"subitem_text_value":"同志社大学,産業技術総合研究所"},{"subitem_text_value":"産総研"}]},"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/230016/files/IPSJ-Z85-5S-05.pdf","label":"IPSJ-Z85-5S-05.pdf"},"date":[{"dateType":"Available","dateValue":"2023-11-17"}],"format":"application/pdf","filename":"IPSJ-Z85-5S-05.pdf","filesize":[{"value":"444.0 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"4b727bb4-4170-40c7-ac70-822e9fd8ce47","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"大田, 竹蔵"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"坂東, 宜昭"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"井本, 桂右"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"大西, 正輝"}],"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":"本稿では自己教師あり学習に基づく音響イベント検出 (SED) について述べる.混合音から音響イベントの種類と発生時刻を推定するSEDは,これまで膨大なアノテーションコストを要する課題があった.そこで本研究では,視聴覚情報を用いた自己教師あり学習(AV-SSL)に基づくSEDの構築法を提案する.音響信号と動画の共起関係を学習するAV-SSLは,音響イベントの識別に有効であることが知られている.SEDの弱教師あり学習における知見を活用し,AV-SSLの学習済みモデルから音響イベントの発生時刻を推定する.動画配信サービスから収集した映像データセットを用いて提案手法の有効性を確認した.","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"442","bibliographic_titles":[{"bibliographic_title":"第85回全国大会講演論文集"}],"bibliographicPageStart":"441","bibliographicIssueDates":{"bibliographicIssueDate":"2023-02-16","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2023"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":230016,"links":{}}