{"links":{},"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00231308","sets":["1164:5159:11151:11431"]},"path":["11431"],"owner":"44499","recid":"231308","title":["Self-supervised learning model based emotion transfer and intensity control technology for expressive speech synthesis"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-11-25"},"_buckets":{"deposit":"abd922d1-7b27-4cc0-b1c4-4dd138657129"},"_deposit":{"id":"231308","pid":{"type":"depid","value":"231308","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Self-supervised learning model based emotion transfer and intensity control technology for expressive speech synthesis","author_link":["624253","624249","624250","624254","624251","624252"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Self-supervised learning model based emotion transfer and intensity control technology for expressive speech synthesis"},{"subitem_title":"Self-supervised learning model based emotion transfer and intensity control technology for expressive speech synthesis","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"ポスター","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2023-11-25","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/231308/files/IPSJ-SLP23149016.pdf","label":"IPSJ-SLP23149016.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP23149016.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":"3abd1db8-8ce9-49b0-a5cb-f98ce01a56f9","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 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":"Wei, Li"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Nobuaki, Minematsu"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Daisuke, Saito"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Wei, Li","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Nobuaki, Minematsu","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Daisuke, Saito","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":"Emotion transfer techniques, which transfersba the speaking style from the reference speech to the target speech, are widely used for speech synthesis. However, previous methods using emotion classifier to disentangle the emotion components fail to transfer the correct emotion to the target speech in some contexts. To solve this problem, we introduce self-supervised learning model to improve the capability of emotion feature extraction. In addition, we utilize the relative attributes method to obtain the intensity labels for our emotional speech dataset. Experimental results indicate that our method can improve the performance of emotional speech synthesis model.","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Emotion transfer techniques, which transfersba the speaking style from the reference speech to the target speech, are widely used for speech synthesis. However, previous methods using emotion classifier to disentangle the emotion components fail to transfer the correct emotion to the target speech in some contexts. To solve this problem, we introduce self-supervised learning model to improve the capability of emotion feature extraction. In addition, we utilize the relative attributes method to obtain the intensity labels for our emotional speech dataset. Experimental results indicate that our method can improve the performance of emotional speech synthesis model.","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":"2023-11-25","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"16","bibliographicVolumeNumber":"2023-SLP-149"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"updated":"2025-01-19T10:48:57.185977+00:00","created":"2025-01-19T01:31:32.007638+00:00","id":231308}