{"created":"2025-01-19T01:29:24.199080+00:00","updated":"2025-01-19T11:21:13.934016+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00229941","sets":["6504:11436:11440"]},"path":["11440"],"owner":"44499","recid":"229941","title":["口パク動画の発話内容推測における距離学習に基づく精度向上手法"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-02-16"},"_buckets":{"deposit":"7487e256-2ecb-4324-aa8a-74ffc17fa4c9"},"_deposit":{"id":"229941","pid":{"type":"depid","value":"229941","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"口パク動画の発話内容推測における距離学習に基づく精度向上手法","author_link":["618597","618595","618596"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"口パク動画の発話内容推測における距離学習に基づく精度向上手法"}]},"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":"早大"},{"subitem_text_value":"早大"},{"subitem_text_value":"早稲田大学理工学術院総合研究所"}]},"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/229941/files/IPSJ-Z85-1R-03.pdf","label":"IPSJ-Z85-1R-03.pdf"},"date":[{"dateType":"Available","dateValue":"2023-11-17"}],"format":"application/pdf","filename":"IPSJ-Z85-1R-03.pdf","filesize":[{"value":"473.4 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"44490221-8c51-4424-ac52-d4af5f81ea19","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":"柏木, 爽良"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"田中, 啓太郎"}],"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":"本稿では，声を出さない口パク時の唇の動画から発話内容を推測する手法を提案する．一般に唇の動きは，声を出す通常の話し方（有声動作）と声を出さない口パク時の話し方（無声動作）とで異なる．しかし，既存データセットの多くは有声動作で構成され，無声動作の発話内容を推測する場合も有声動作データセットで訓練されたモデルが使用されるため，無声動作に対する予測精度が有声動作に対する予測精度を大きく下回る問題がある．有声動作と無声動作の違いを吸収し同等精度での予測を実現するため，唇の動きの最小単位であるvisemeに対し距離学習を行う枠組みを提案する．実験を通し，無声動作に対して3%以上精度が向上することを示す．","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"288","bibliographic_titles":[{"bibliographic_title":"第85回全国大会講演論文集"}],"bibliographicPageStart":"287","bibliographicIssueDates":{"bibliographicIssueDate":"2023-02-16","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2023"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":229941,"links":{}}