{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00236048","sets":["6504:11678:11689"]},"path":["11689"],"owner":"44499","recid":"236048","title":["音声認識の音響特徴を用いた音声感情認識システムの構築と分類精度向上に関する検討"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-03-01"},"_buckets":{"deposit":"bf04f121-a1de-4945-95c5-d4f74b59ef94"},"_deposit":{"id":"236048","pid":{"type":"depid","value":"236048","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"音声認識の音響特徴を用いた音声感情認識システムの構築と分類精度向上に関する検討","author_link":["645097","645098","645095","645099","645096"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"音声認識の音響特徴を用いた音声感情認識システムの構築と分類精度向上に関する検討"}]},"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":"電機大"},{"subitem_text_value":"電機大"},{"subitem_text_value":"東大"},{"subitem_text_value":"電機大"},{"subitem_text_value":"電機大"}]},"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/236048/files/IPSJ-Z86-5R-04.pdf","label":"IPSJ-Z86-5R-04.pdf"},"date":[{"dateType":"Available","dateValue":"2024-07-03"}],"format":"application/pdf","filename":"IPSJ-Z86-5R-04.pdf","filesize":[{"value":"316.4 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"238524ce-297c-4dd7-91ba-573a40ebaa23","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":"中村, 優太"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"高野, 毅"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"鄭, 雄一"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"高橋, 達二"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"篠原, 修二"}],"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":"人間と機械の音声によるコミュニケーションでは, 話し手の感情や意図の理解が重要である. 本研究では, 心理学の基本感情説に基づき, 音声認識のw2v2-l-robustモデルの隠れ層を音響特徴としてNNや決定木を用いた喜怒哀の3感情の強度を推定する音声感情認識システムを構築した. MSP-Podcastデータセットで学習を行い, IEMOCAPデータセットで検証を行なった. さらに感情ごとに推定値のばらつきがあることに着目し, Youden indexを用いたカットオフを揃える手法を考案した. その結果, この手法で分類精度を向上できる可能性が示唆された.","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"412","bibliographic_titles":[{"bibliographic_title":"第86回全国大会講演論文集"}],"bibliographicPageStart":"411","bibliographicIssueDates":{"bibliographicIssueDate":"2024-03-01","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2024"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":236048,"updated":"2025-01-19T09:24:56.739179+00:00","links":{},"created":"2025-01-19T01:37:53.323205+00:00"}