{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00214921","sets":["6504:10735:10808"]},"path":["10808"],"owner":"44499","recid":"214921","title":["アンサンブル時間周波数マスクによる音声強調手法の検討"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-03-04"},"_buckets":{"deposit":"81832437-bd0e-4ada-afe5-136e1a68d982"},"_deposit":{"id":"214921","pid":{"type":"depid","value":"214921","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"アンサンブル時間周波数マスクによる音声強調手法の検討","author_link":["553132","553134","553131","553133"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"アンサンブル時間周波数マスクによる音声強調手法の検討"}]},"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":"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":"東工大"},{"subitem_text_value":"東工大"},{"subitem_text_value":"東工大"},{"subitem_text_value":"東工大/ホンダRIJ"}]},"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/214921/files/IPSJ-Z83-7N-06.pdf","label":"IPSJ-Z83-7N-06.pdf"},"date":[{"dateType":"Available","dateValue":"2021-12-28"}],"format":"application/pdf","filename":"IPSJ-Z83-7N-06.pdf","filesize":[{"value":"369.1 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"86a68027-e86a-40f1-b93d-66e928ce5cec","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":"藤田, 雅彦"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"糸山, 克寿"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"西田, 健次"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"中臺, 一博"}],"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, アンサンブル時間周波数マスクを用いたビームフォーミングに基づく音声強調手法を報告する. 従来の時間周波数マスクベースの音声強調手法は, 単一のキューから時間周波数マスク推定していたため，十分に入力信号に含まれる音声強調の鍵となる特徴量を活かしきれていなかった．そこで，異なるキューから推定される複数の時間周波数マスクを統合して処理のロバスト性を向上するアンサンブル時間周波数マスク法を提案する. 提案手法をCHiME3コーパスを使って, 人間の聴感と相関があるPESQとSTOIを用いて評価した. いずれの評価指標においても提案手法がアンサンブルを行わない既存手法を上回り, 提案手法の有効性を示した.","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"236","bibliographic_titles":[{"bibliographic_title":"第83回全国大会講演論文集"}],"bibliographicPageStart":"235","bibliographicIssueDates":{"bibliographicIssueDate":"2021-03-04","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2021"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":214921,"updated":"2025-01-19T16:24:21.754985+00:00","links":{},"created":"2025-01-19T01:15:42.716885+00:00"}