{"created":"2025-01-19T01:27:39.705790+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00228518","sets":["6164:6165:7006:11378"]},"path":["11378"],"owner":"44499","recid":"228518","title":["重複音声のクラウド音声認識への影響評価"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-10-18"},"_buckets":{"deposit":"2d919c13-07d8-4f84-a7a4-d6ff5f9e869d"},"_deposit":{"id":"228518","pid":{"type":"depid","value":"228518","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"重複音声のクラウド音声認識への影響評価","author_link":["610025","610026","610028","610027"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"重複音声のクラウド音声認識への影響評価"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"字幕作成，重複音声","subitem_subject_scheme":"Other"}]},"item_type_id":"18","publish_date":"2023-10-18","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_18_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"同志社大学大学院"},{"subitem_text_value":"同志社大学大学院"},{"subitem_text_value":"同志社大学"},{"subitem_text_value":"同志社大学大学院"}]},"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/228518/files/IPSJ-DPSWS20230019.pdf","label":"IPSJ-DPSWS20230019.pdf"},"date":[{"dateType":"Available","dateValue":"2025-10-18"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-DPSWS20230019.pdf","filesize":[{"value":"1.0 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":"34"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"80505f5f-7cd9-4f61-a967-5ba5ec969cad","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 by the Information Processing Society of Japan"}]},"item_18_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"中平, 一六"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"黒岩, 舜"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"大島, 千尋"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"小板, 隆浩"}],"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_18_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"本研究は，動画の字幕生成における既存システムの性能評価に焦点を当てる．特に，動画の時間長と重複音声の出現回数が性能に与える影響を詳細に調査した．分析には，Word Error Rate（WER）と BERTScore という二つの評価指標を用いた．結果として，短い動画で重複音声が多く出現する場合に性能が顕著に低下することが明らかになった．これを踏まえ，人間と機械の協働による新しい字幕生成手法を提案する．さらに，今後の研究の方向性として，新たな評価指標や重複音声の発生した時間を考慮する方法も示す．この研究は，字幕生成技術の精度向上に貢献するものであり，多くの動画コンテンツを活用する現代社会において，その重要性はますます高まっている．","subitem_description_type":"Other"}]},"item_18_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"143","bibliographic_titles":[{"bibliographic_title":"第31回マルチメディア通信と分散処理ワークショップ論文集"}],"bibliographicPageStart":"138","bibliographicIssueDates":{"bibliographicIssueDate":"2023-10-18","bibliographicIssueDateType":"Issued"}}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":228518,"updated":"2025-01-19T11:49:32.544554+00:00","links":{}}