{"links":{},"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00216610","sets":["1164:5159:10869:10870"]},"path":["10870"],"owner":"44499","recid":"216610","title":["多話者音声合成のためのAdversarial Regularizer を考慮した学習アルゴリズム"],"pubdate":{"attribute_name":"公開日","attribute_value":"2022-02-22"},"_buckets":{"deposit":"9bf44164-6854-44e7-b05e-4fb6488dbd8b"},"_deposit":{"id":"216610","pid":{"type":"depid","value":"216610","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"多話者音声合成のためのAdversarial Regularizer を考慮した学習アルゴリズム","author_link":["559227","559234","559232","559231","559229","559228","559233","559230"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"多話者音声合成のためのAdversarial Regularizer を考慮した学習アルゴリズム"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"SP1","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2022-02-22","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東京大学"},{"subitem_text_value":"東京大学"},{"subitem_text_value":"東京大学"},{"subitem_text_value":"東京大学"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"The University of Tokyo","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"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/216610/files/IPSJ-SLP22140009.pdf","label":"IPSJ-SLP22140009.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP22140009.pdf","filesize":[{"value":"1.6 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"22"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"eec306af-3c4d-45d4-80c5-363f34a53481","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2022 by the Institute of Electronics, Information and Communication Engineers This SIG report is only available to those in membership of the SIG."}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"仲井, 佑友輔"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"齋藤, 佑樹"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"宇田川, 健太"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"猿渡, 洋"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Yusuke, Nakai","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yuki, Saito","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Kenta, Udagawa","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hiroshi, Saruwatari","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10442647","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8663","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"本稿では，Adversarial Reguralizer を考慮した敵対学習による多話者音声合成モデルを提案する．従来法では，識別的なタスクによって事前学習した Speaker Encoder から目的話者の話者埋め込みを抽出し，音声合成ネットワークに入力を行う．しかし，学習された話者埋め込みの分布する特徴量空間は音声合成ネットワークにとって必ず しも解釈性が高いとは限らず，未知話者の話者埋め込みを上手く抽出できる保証が無いという問題があった．提案法 では，事前学習済みの話者埋め込み空間をうまく解釈できる音声合成ネットワークの構築を目的とし，学習アルゴリ ズムとして Adversarial Reguralizer を考慮した敵対学習を提案する．提案法では，話者埋め込みを混合して合成した音声の特徴量と，自然音声の特徴量が識別不可能となるような正則化項を考慮して音声合成ネットワークを学習する． 実験的評価により，提案法が合成音声の話者類似性と，話者モーフィングの操作性を改善する傾向にあることを示す．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告音声言語情報処理（SLP）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2022-02-22","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"9","bibliographicVolumeNumber":"2022-SLP-140"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"updated":"2025-01-19T15:47:41.373390+00:00","created":"2025-01-19T01:17:08.067944+00:00","id":216610}