{"created":"2025-01-19T01:37:53.141162+00:00","updated":"2025-01-19T09:24:59.728380+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00236046","sets":["6504:11678:11689"]},"path":["11689"],"owner":"44499","recid":"236046","title":["音声とテキストのクロスモーダルTransformer エンコーダに基づく音声区間毎の感情認識"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-03-01"},"_buckets":{"deposit":"0ea42cb8-501d-4ba7-bcfc-900cefdf56d9"},"_deposit":{"id":"236046","pid":{"type":"depid","value":"236046","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"音声とテキストのクロスモーダルTransformer エンコーダに基づく音声区間毎の感情認識","author_link":["645092","645091"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"音声とテキストのクロスモーダルTransformer エンコーダに基づく音声区間毎の感情認識"}]},"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":"2024-03-01","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":"創価大"},{"subitem_text_value":"創価大"}]},"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/236046/files/IPSJ-Z86-5R-02.pdf","label":"IPSJ-Z86-5R-02.pdf"},"date":[{"dateType":"Available","dateValue":"2024-07-03"}],"format":"application/pdf","filename":"IPSJ-Z86-5R-02.pdf","filesize":[{"value":"670.5 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"3aefa5a8-03fc-4d22-b50b-4fc3567ea519","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"仁平, 正彦"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"渥美, 雅保"}],"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":"マルチモーダル感情表現認識では，複数のモダリティを融合する手法やデータセットの不足等の課題が存在する．本研究では，音声のWav2vec 2.0によるエンコーディングと音声認識モデルWhisperによる文字起こしテキストのRoBERTaによるエンコーディングを入力とするクロスモーダルTransformerエンコーダに基づく感情認識モデルを提案する．そして，音声区間毎の感情認識とその合議による全体の感情認識を扱う．そのために，音声区間毎に感情ラベル付けした小規模データセットを作成し，音声区間毎，及び合議による全体の感情識別性能を評価する．更に，データクレンジングとデータに含まれる感情数に基づく2段階の学習により，高精度な認識が可能であるか検証する．","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"408","bibliographic_titles":[{"bibliographic_title":"第86回全国大会講演論文集"}],"bibliographicPageStart":"407","bibliographicIssueDates":{"bibliographicIssueDate":"2024-03-01","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2024"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":236046,"links":{}}