{"updated":"2025-01-19T18:53:44.611170+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00208183","sets":["1164:5159:10092:10413"]},"path":["10413"],"owner":"44499","recid":"208183","title":["StarGANに基づく話者変換の基本周波数系列の安定化"],"pubdate":{"attribute_name":"公開日","attribute_value":"2020-11-25"},"_buckets":{"deposit":"a753e698-87c6-47ee-9b1d-379964b5dda6"},"_deposit":{"id":"208183","pid":{"type":"depid","value":"208183","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"StarGANに基づく話者変換の基本周波数系列の安定化","author_link":["521079","521077","521076","521078"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"StarGANに基づく話者変換の基本周波数系列の安定化"},{"subitem_title":"Stabilize Foundamental Frequency of StarGAN based Voice Conversion System","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"音声分析・変換・検出","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2020-11-25","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"Convergence Lab. 株式会社"},{"subitem_text_value":"時空テクノロジーズ株式会社"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Convergence Lab. Inc.","subitem_text_language":"en"},{"subitem_text_value":"ZIKU technologies Inc.","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/208183/files/IPSJ-SLP20134034.pdf","label":"IPSJ-SLP20134034.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP20134034.pdf","filesize":[{"value":"1.0 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"22"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"60235078-465d-42ea-a2d0-2f6b29303662","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2020 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"木村, 優志"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"春日, 秀之"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Masashi, Kimura","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hideyuki, Kasuga","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":"コンピューターグラフィックスで作られた外見で動画配信を行う Virtual Youtuber (VTuber / バーチャルライバー) や，Virtual Influencer と呼ばれる存在が近年注目されている．CG による固有の外観をもっているが，声に関しては声優などが務めることが多い．ここで，バーチャルタレントの外見だけではなく，話者変換によって声を変えることができればより便利である．StarGAN-VC2++ は高精度な話者変換モデルの一つであるが，基本周波数が振動するという問題がある．そこで，新たに Δ????0 損失項を導入し，基本周波数の振動の抑制を試みる．実験の結果，基本周波数の振動の抑制が確認された．しかし，フィルタが発振する例が見られる問題が残る．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Virtual Youtuber and Virtual Influencer is getting attention, which is video streamers with avator appearence created computer graphics. They have unique appearance, however regarding the voice, usually voice actor plays. It would be usefull not only changing appearance but also changing voice with voice converter. StarGAN-VC2++ is a high quality voice converter, however has a problem of ????0 vibration. We propose Δ????0 loss term to reduce ????0 vibration. Experimental result shows that ????0 loss term reduces ????0 vibration, however sometimes filter oscillates.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"4","bibliographic_titles":[{"bibliographic_title":"研究報告音声言語情報処理（SLP）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2020-11-25","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"34","bibliographicVolumeNumber":"2020-SLP-134"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"created":"2025-01-19T01:09:45.902957+00:00","id":208183,"links":{}}