{"links":{},"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00164252","sets":["6504:8291:8755"]},"path":["8755"],"owner":"6748","recid":"164252","title":["Deep Neural Networkを用いた雑音抑圧及びブラインド音源分離手法の提案とその評価"],"pubdate":{"attribute_name":"公開日","attribute_value":"2015-03-17"},"_buckets":{"deposit":"7254f4b8-b1e1-4122-9061-2a28f3ff2515"},"_deposit":{"id":"164252","pid":{"type":"depid","value":"164252","revision_id":0},"owners":[6748],"status":"published","created_by":6748},"item_title":"Deep Neural Networkを用いた雑音抑圧及びブラインド音源分離手法の提案とその評価","author_link":["323294","323296","323295","323297"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Deep Neural Networkを用いた雑音抑圧及びブラインド音源分離手法の提案とその評価"}]},"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":"2015-03-17","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":"早大"},{"subitem_text_value":"早大"},{"subitem_text_value":"ホンダRIJ"},{"subitem_text_value":"早大"}]},"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/164252/files/IPSJ-Z77-5P-01.pdf","label":"IPSJ-Z77-5P-01.pdf"},"date":[{"dateType":"Available","dateValue":"2016-06-14"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-Z77-5P-01.pdf","filesize":[{"value":"497.8 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"8"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"074496d2-ae1c-4ee8-a243-ddb41582e3d1","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2015 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"橋本, 直矢"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"野田, 邦昭"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"中臺, 一博"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"尾形, 哲也"}],"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":"従来音源分離には独立成分分析等の手法を用いることが一般的であったが，分離フィルタが線形写像となるためその性能には限界があった．本研究では任意の非線形写像を近似できるDeep Neural Network (DNN)を分離フィルタ及び雑音抑圧のモデルとして用いる手法を提案する．提案モデルでは，マイクロホンアレイにより収録した混合音声信号の多チャンネルメルフィルタバンク特徴を入力，目的の音源の音響特徴を出力としてDNNを学習し，分離フィルタをモデル化した．DNNの構造や音響特徴量等の条件を，隠れ層の数やSN比を変化させて評価実験を行った結果，多くの場合において提案手法が従来の方法より高い性能を示す事を確認した．","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"116","bibliographic_titles":[{"bibliographic_title":"第77回全国大会講演論文集"}],"bibliographicPageStart":"115","bibliographicIssueDates":{"bibliographicIssueDate":"2015-03-17","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2015"}]},"relation_version_is_last":true,"weko_creator_id":"6748"},"updated":"2025-01-20T10:56:27.042548+00:00","created":"2025-01-19T00:36:05.339203+00:00","id":164252}