{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00234654","sets":["1164:5064:11558:11626"]},"path":["11626"],"owner":"44499","recid":"234654","title":["母語話者音声コーパスのみを用いた自己教師あり学習による外国語訛り音声の合成"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-06-07"},"_buckets":{"deposit":"80712ad8-684b-478e-bf71-576d4f8978b9"},"_deposit":{"id":"234654","pid":{"type":"depid","value":"234654","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"母語話者音声コーパスのみを用いた自己教師あり学習による外国語訛り音声の合成","author_link":["639676","639679","639678","639677"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"母語話者音声コーパスのみを用いた自己教師あり学習による外国語訛り音声の合成"},{"subitem_title":"Synthesis of Foreign Accented Speech by Self-supervised Learning Only Using Native Speech Corpora","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"招待講演5","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":"東京大学工学系研究科"},{"subitem_text_value":"東京大学工学系研究科"},{"subitem_text_value":"東京大学工学系研究科"},{"subitem_text_value":"東京大学工学系研究科"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"UTokyo","subitem_text_language":"en"},{"subitem_text_value":"UTokyo","subitem_text_language":"en"},{"subitem_text_value":"UTokyo","subitem_text_language":"en"},{"subitem_text_value":"UTokyo","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/234654/files/IPSJ-MUS24140042.pdf","label":"IPSJ-MUS24140042.pdf"},"date":[{"dateType":"Available","dateValue":"2026-06-07"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-MUS24140042.pdf","filesize":[{"value":"1.2 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"21"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"7395056b-dd33-47e3-889a-0dce5b63de43","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":"恩田, 健太郎"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"朴, 浚鎔"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"齋藤, 大輔"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"峯松, 信明"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10438388","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":"2188-8752","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"ある言語の母語話者音声コーパスのみを用いた自己教師あり学習により，その言語に固有の音韻表象と解釈できる離散シンボルを生成し，音声→離散シンボル列→音声と再合成を行うことで，その言語特有の訛りが他言語入力に対して付与されるプロセスを模擬する．出力音声は，特に分節的な観点において，実際の L2 話者の発話と類似した訛りの傾向を持つことが示された．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"In this paper, we simulate the process of foreign accentuation by generating discrete symbols that can be interpreted as language-specific phonological representations using self-supervised learning only with native speech corpora. The output speech, which is synthesized by the process of speech → discrete symbol sequence → speech, was shown to have similar behaviors of accentuation to that of actual L2 speakers, especially from a segmental perspective.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告音楽情報科学（MUS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2024-06-07","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"42","bibliographicVolumeNumber":"2024-MUS-140"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":234654,"updated":"2025-01-19T09:44:12.138836+00:00","links":{},"created":"2025-01-19T01:36:30.274495+00:00"}