{"id":234734,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00234734","sets":["1164:5159:11541:11627"]},"path":["11627"],"owner":"44499","recid":"234734","title":["Cross-lingual Singing Voice Conversion Leveraging Transformer-based ASR Encoder"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-06-07"},"_buckets":{"deposit":"f85cdff8-02da-46a3-b7a7-8b361a4b9bb6"},"_deposit":{"id":"234734","pid":{"type":"depid","value":"234734","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Cross-lingual Singing Voice Conversion Leveraging Transformer-based ASR Encoder","author_link":["640035","640034","640038","640033","640037","640036"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Cross-lingual Singing Voice Conversion Leveraging Transformer-based ASR Encoder"},{"subitem_title":"Cross-lingual Singing Voice Conversion Leveraging Transformer-based ASR Encoder","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"ポスターセッション2","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2024-06-07","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Engineering, The University of Tokyo"},{"subitem_text_value":"Graduate School of Engineering, The University of Tokyo"},{"subitem_text_value":"Graduate School of Engineering, The University of Tokyo"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Engineering, The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Engineering, The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Engineering, The University of Tokyo","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"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/234734/files/IPSJ-SLP24152047.pdf","label":"IPSJ-SLP24152047.pdf"},"date":[{"dateType":"Available","dateValue":"2026-06-07"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP24152047.pdf","filesize":[{"value":"920.6 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"22"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"11273950-c51f-4d77-a8b7-85c618c9bd89","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Xinyuan, Zhao"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Daisuke, Saito"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Nobuaki, Minematsu"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Xinyuan, Zhao","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Daisuke, Saito","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Nobuaki, Minematsu","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":"In this paper, we focus on singing voice conversion task, including monolingual and cross-lingual singing voice conversion. We proposed a method to modify MaskCycleGAN, a model designed for nonparallel speech conversion task, and applied the proposed model for the singing voice conversion task. The new model concatenates MaskCycleGAN with Whisper, a transformer-based ASR encoder that recognizes the content of the song. The experimental results demonstrated significant performance improvements over the original MaskCycleGAN in both monolingual and cross-lingual scenarios for the singing voice conversion task.","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":"2024-06-07","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"47","bibliographicVolumeNumber":"2024-SLP-152"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"updated":"2025-01-19T09:42:35.009071+00:00","created":"2025-01-19T01:36:37.802582+00:00","links":{}}