{"created":"2021-03-01T06:21:32.965296+00:00","id":4869,"links":{},"metadata":{"_buckets":{"deposit":"fb2eaf0a-8c6c-46a6-b208-5d0e3f895a0e"},"_deposit":{"id":"4869","owners":[],"pid":{"revision_id":0,"type":"depid","value":"4869"},"status":"published"},"_oai":{"id":"oai:repository.dl.itc.u-tokyo.ac.jp:00004869","sets":["6:209:271","9:233:234"]},"item_7_alternative_title_1":{"attribute_name":"その他のタイトル","attribute_value_mlt":[{"subitem_alternative_title":"Unsupervised Learning of Speech Bases and Phone Classification Using Convolutive Non-negative Matrix Factorization"}]},"item_7_biblio_info_7":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"2013-03-25","bibliographicIssueDateType":"Issued"},"bibliographic_titles":[{}]}]},"item_7_date_granted_25":{"attribute_name":"学位授与年月日","attribute_value_mlt":[{"subitem_dategranted":"2013-03-25"}]},"item_7_degree_name_20":{"attribute_name":"学位名","attribute_value_mlt":[{"subitem_degreename":"修士(工学)"}]},"item_7_description_5":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"知覚情報に含まれる基底を教師無しで学習させると, その結果が人間の脳内での処理と類似することが明らかにされている. このために教師無し学習は, 知覚情報処理の分野でとても注目されている. 音情報処理においては, 教師無し学習の一つである非負値行列分解(NMF) が楽器音の抽出や音声の話者分離の研究で成果を上げている.本稿ではNMF を改良したモデルの一つである畳み込み非負値行列分解(CNMF) を用いて, 音声の基底を抽出する手法を提案する. CNMF により抽出した音声の基底を用いた音素分類実験の結果, 音声の中に含まれる音韻情報を学習出来ることを確かめた. またCNMF のパラメータを最適化する手法として, 従来の補助関数法を用いた手法よりもCoordinate Descent を用いた手法の方がより速く最適解が求まることを示した.","subitem_description_type":"Abstract"}]},"item_7_full_name_3":{"attribute_name":"著者別名","attribute_value_mlt":[{"nameIdentifiers":[{"nameIdentifier":"10573","nameIdentifierScheme":"WEKO"}],"names":[{"name":"Hariya, Wataru"}]}]},"item_7_select_21":{"attribute_name":"学位","attribute_value_mlt":[{"subitem_select_item":"master"}]},"item_7_text_24":{"attribute_name":"研究科・専攻","attribute_value_mlt":[{"subitem_text_value":"工学系研究科・電気系工学専攻"}]},"item_7_text_4":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東京大学大学院工学系研究科電気系工学専攻"},{"subitem_text_value":"Department of Electrical Engineering and Information Systems, Graduate School of Engineering, The University of Tokyo"}]},"item_creator":{"attribute_name":"著者","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"針谷, 航"}],"nameIdentifiers":[{"nameIdentifier":"10572","nameIdentifierScheme":"WEKO"}]}]},"item_files":{"attribute_name":"ファイル情報","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_date","date":[{"dateType":"Available","dateValue":"2017-06-01"}],"displaytype":"detail","filename":"37106488.pdf","filesize":[{"value":"567.0 kB"}],"format":"application/pdf","licensetype":"license_note","mimetype":"application/pdf","url":{"label":"37106488.pdf","url":"https://repository.dl.itc.u-tokyo.ac.jp/record/4869/files/37106488.pdf"},"version_id":"9272e977-4d15-43ff-b175-19c91c7b6daa"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourcetype":"thesis","resourceuri":"http://purl.org/coar/resource_type/c_46ec"}]},"item_title":"畳み込み非負値行列分解を用いた音声の基底の教師無し学習と音素分類","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"畳み込み非負値行列分解を用いた音声の基底の教師無し学習と音素分類"}]},"item_type_id":"7","owner":"1","path":["234","271"],"pubdate":{"attribute_name":"公開日","attribute_value":"2013-05-07"},"publish_date":"2013-05-07","publish_status":"0","recid":"4869","relation_version_is_last":true,"title":["畳み込み非負値行列分解を用いた音声の基底の教師無し学習と音素分類"],"weko_creator_id":"1","weko_shared_id":null},"updated":"2022-12-19T03:46:32.402268+00:00"}