{"updated":"2025-01-19T16:24:37.350746+00:00","links":{},"created":"2025-01-19T01:15:42.154932+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00214911","sets":["6504:10735:10808"]},"path":["10808"],"owner":"44499","recid":"214911","title":["プレゼンテーションにおけるスライド情報を用いた音声認識結果の自動修正"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-03-04"},"_buckets":{"deposit":"18f6c7fe-308f-4a7a-bae9-980b78d31e72"},"_deposit":{"id":"214911","pid":{"type":"depid","value":"214911","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"プレゼンテーションにおけるスライド情報を用いた音声認識結果の自動修正","author_link":["553093","553094","553095","553096"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"プレゼンテーションにおけるスライド情報を用いた音声認識結果の自動修正"}]},"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":"2021-03-04","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":"名大"},{"subitem_text_value":"名大"},{"subitem_text_value":"名大"},{"subitem_text_value":"名大"}]},"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/214911/files/IPSJ-Z83-6N-03.pdf","label":"IPSJ-Z83-6N-03.pdf"},"date":[{"dateType":"Available","dateValue":"2021-12-28"}],"format":"application/pdf","filename":"IPSJ-Z83-6N-03.pdf","filesize":[{"value":"385.9 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"e3b3e15a-60ca-44ce-939b-f0a3713f213d","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2021 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"神谷, 賢太郎"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"東中, 竜一郎"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"川瀬, 卓也"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"長尾, 確"}],"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":"プレゼンテーションの発表者の発言を高精度で音声認識することは，多くの専門用語が使用されることなどから困難である．そこで，本研究では，プレゼンテーションで使用されるスライド情報と認識対象の周辺の発言を補足情報として用い，音声認識結果を修正することで音声認識精度の改善を試みる．この修正には，深層学習モデルを用い，音声認識結果と補足情報から抽出した特徴量を入力とし，音声認識結果の正解を出力するようにモデルの学習を行う．実際のプレゼンテーションデータを対象とした実験の結果，提案手法が音声認識精度の改善につながることを確認した．","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"216","bibliographic_titles":[{"bibliographic_title":"第83回全国大会講演論文集"}],"bibliographicPageStart":"215","bibliographicIssueDates":{"bibliographicIssueDate":"2021-03-04","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2021"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":214911}