{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00236023","sets":["6504:11678:11689"]},"path":["11689"],"owner":"44499","recid":"236023","title":["距離ベース時間周波数マスク推定による音声強調手法の検討"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-03-01"},"_buckets":{"deposit":"90621d1e-0012-4d8c-8a28-2230db2c68ce"},"_deposit":{"id":"236023","pid":{"type":"depid","value":"236023","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"距離ベース時間周波数マスク推定による音声強調手法の検討","author_link":["645012","645011","645013"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"距離ベース時間周波数マスク推定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":"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":"東工大"},{"subitem_text_value":"東工大"},{"subitem_text_value":"東京工業大/HRI-JP"}]},"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/236023/files/IPSJ-Z86-1R-04.pdf","label":"IPSJ-Z86-1R-04.pdf"},"date":[{"dateType":"Available","dateValue":"2024-07-03"}],"format":"application/pdf","filename":"IPSJ-Z86-1R-04.pdf","filesize":[{"value":"1.2 MB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"630eeceb-58c5-4c10-992d-c01d7eb9aeaa","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":"石井, 遼平"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"中臺, 一博"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"糸山, 克寿"}],"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":"一般に会議では、複数の人が集まって話をするため、たとえ各話者の口元にマイクをつけて収録した場合でも、収録音には対象話者の音声に加え、他の話者の音声が混入してしまう。このため、収録音中の対象話者の音声の聴取が困難になり、議事録作成などの用途に支障をきたすという問題がある。本稿では、この問題を解決するため、ディープラーニングにより推定された時間周波数マスクを用いて、モノラル収録音から、近距離話者の音声のみを抽出する音声強調法を提案する。提案手法を人間の聴覚と相関があるPESQとSTOIを用いて評価した結果、提案手法の有効性を示すことができた。","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"362","bibliographic_titles":[{"bibliographic_title":"第86回全国大会講演論文集"}],"bibliographicPageStart":"361","bibliographicIssueDates":{"bibliographicIssueDate":"2024-03-01","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2024"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":236023,"updated":"2025-01-19T09:25:31.726801+00:00","links":{},"created":"2025-01-19T01:37:51.025572+00:00"}