{"updated":"2025-01-19T07:32:53.238964+00:00","links":{},"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00241806","sets":["1164:8666:11564:11871"]},"path":["11871"],"owner":"44499","recid":"241806","title":["Transformerを用いた連続指文字認識の精度向上に関する研究―CNN-LSTM複合モデルとの比較分析―"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-12-16"},"_buckets":{"deposit":"e4d7a1a9-97ec-43fd-8887-a2013831300e"},"_deposit":{"id":"241806","pid":{"type":"depid","value":"241806","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Transformerを用いた連続指文字認識の精度向上に関する研究―CNN-LSTM複合モデルとの比較分析―","author_link":["666285","666283","666284","666282"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Transformerを用いた連続指文字認識の精度向上に関する研究―CNN-LSTM複合モデルとの比較分析―"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"セッション3","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2024-12-16","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"筑波技術大学／筑波大学"},{"subitem_text_value":"筑波技術大学"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Tsukuba University of Technology / University of Tsukuba","subitem_text_language":"en"},{"subitem_text_value":"Tsukuba University of Technology","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/241806/files/IPSJ-AAC24026007.pdf","label":"IPSJ-AAC24026007.pdf"},"date":[{"dateType":"Available","dateValue":"2026-12-16"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-AAC24026007.pdf","filesize":[{"value":"3.3 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"52"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"68eff1ed-8d01-4ba9-8ac3-913ee5bfe487","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"設楽, 明寿"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"白石, 優旗"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Akihisa, Shitara","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yuhki, Shiraishi","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA12752949","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":"2432-2431","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"我々は，ろう・難聴者と聴者の円滑なコミュニケーションを実現するため，深層学習を用いたセンサグローブによる連続指文字認識システムを開発してきた．そこでは，CNN と LSTM を組み合わせた学習モデルにおいて，F-measure の micro 平均は 92.1% にもかかわらず，F-measure の macro 平均は 64.7% と報告している．理由としては，静止指文字と動的指文字の識別の困難性，指文字から次に表出する指文字との間である「わたり」のデータが多いことによる指文字の認識率の低下などが挙げられる．そこで，Transformer の使用が指文字の認識率の向上に寄与するかについて，CNN と LSTM を組み合わせた学習モデルをベースラインとして定量的評価を実施した．また，個人差の影響が軽減されているかについて，学習に使用するデータの選別を通じて交差検証による性能評価を行った．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告アクセシビリティ（AAC）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2024-12-16","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"7","bibliographicVolumeNumber":"2024-AAC-26"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":241806,"created":"2025-01-19T01:46:37.999536+00:00"}