{"links":{},"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00232473","sets":["1164:5159:11541:11549"]},"path":["11549"],"owner":"44499","recid":"232473","title":["音声品質と音響環境の潜在変数で条件付けたDenoising Trainingによるノイズロバスト音声変換"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-02-22"},"_buckets":{"deposit":"6d8fc1da-9e13-4f67-89ab-f38cd7ca8f38"},"_deposit":{"id":"232473","pid":{"type":"depid","value":"232473","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"音声品質と音響環境の潜在変数で条件付けたDenoising Trainingによるノイズロバスト音声変換","author_link":["629273","629261","629269","629272","629265","629264","629268","629274","629271","629262","629266","629263","629267","629270"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"音声品質と音響環境の潜在変数で条件付けたDenoising Trainingによるノイズロバスト音声変換"}]},"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":"2024-02-22","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"},{"subitem_text_value":"LINEヤフー株式会社"},{"subitem_text_value":"LINEヤフー株式会社"},{"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"},{"subitem_text_value":" LY Corporation","subitem_text_language":"en"},{"subitem_text_value":" LY Corporation","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/232473/files/IPSJ-SLP24151003.pdf","label":"IPSJ-SLP24151003.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP24151003.pdf","filesize":[{"value":"1.3 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"22"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"ca574d2a-3e58-4cc8-b257-21a3e6478691","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 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":"五十嵐, 琢斗"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"齋藤, 佑樹"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"関, 健太郎"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"高道, 慎之介"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"山本, 龍一"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"橘, 健太郎"}],"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":"Takuto, Igarashi","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yuki, Saito","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Kentaro, Seki","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shinnosuke, Takamichi","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Ryuichi, Yamamoto","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Kentaro, Tachibana","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,ノイジーな入力音声に対し,その音声品質と音響環境を表現する潜在変数の条件付けを行うノイズロバストな音声変換を提案する.先行研究では,クリーン音声に雑音や残響を人工的に付加することで得た疑似ノイジー音声のデータから noisy-to-clean の音声変換を学習する denoising training と呼ばれる手法により,既存のモデル構造に変更を加えることなく,ノイズロバストな音声変換を提案した.しかし,この手法は音声変換モデルが入力音声の多様な雑音や品質劣化を十分に学習できないため,推論時に未知ノイズで劣化した入力音声に対して,変換された音声の音韻や韻律が乱れる傾向にある.本研究では,入力音声の品質・雑音の多様性を解釈する機構を取り入れた音声変換を行うことを目的とし,denoising training の際に入力音声の音声品質および音響環境の潜在変数で条件付けたノイズロバストな音声変換の学習法を提案する.客観および主観評価により,提案手法により変換された音声の品質が従来手法と比較して向上することを示す.","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":"2024-02-22","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"3","bibliographicVolumeNumber":"2024-SLP-151"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"updated":"2025-01-19T10:26:11.219115+00:00","created":"2025-01-19T01:33:21.680544+00:00","id":232473}