{"created":"2025-01-19T01:46:22.005408+00:00","updated":"2025-01-19T07:35:38.711776+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00241642","sets":["1164:5159:11541:11870"]},"path":["11870"],"owner":"44499","recid":"241642","title":["離散トークンの継続長予測に基づく母語話者音声コーパスのみを用いた外国語訛り音声合成手法の改善"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-12-05"},"_buckets":{"deposit":"33ab5c9f-5b19-4c93-b80c-f082804e4c2d"},"_deposit":{"id":"241642","pid":{"type":"depid","value":"241642","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"離散トークンの継続長予測に基づく母語話者音声コーパスのみを用いた外国語訛り音声合成手法の改善","author_link":["665617","665622","665619","665621","665620","665618"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"離散トークンの継続長予測に基づく母語話者音声コーパスのみを用いた外国語訛り音声合成手法の改善"},{"subitem_title":"Improved Foreign Accent Simulation Using Only Native Speech Corpora Based on Discrete Token Duration Prediction","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"音声合成・符号化","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2024-12-05","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東京大学大学院工学系研究科／産業技術総合研究所人工知能研究センター"},{"subitem_text_value":"東京大学大学院工学系研究科"},{"subitem_text_value":"同志社大学文化情報学部"},{"subitem_text_value":"産業技術総合研究所人工知能研究センター"},{"subitem_text_value":"東京大学大学院工学系研究科"},{"subitem_text_value":"東京大学大学院工学系研究科"}]},"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/241642/files/IPSJ-SLP24154022.pdf","label":"IPSJ-SLP24154022.pdf"},"date":[{"dateType":"Available","dateValue":"2026-12-05"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP24154022.pdf","filesize":[{"value":"1.3 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":"22"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"37b7dea5-8cb6-4dfe-85d1-16fd48a685c3","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":"井本, 桂右"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"深山, 覚"}],"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":"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":"離散トークンを中間表現とした音声の再合成により外国語訛り音声を合成する従来手法の改善を行った．従来手法では，出力音声が入力音声の時間構造を保持してしまうために実際の話者に見られるような音素継続長に関する訛りを再現できないという問題点があったが，離散トークンベースでの継続長修正モジュールを追加することで，出力音声において継続長に関する訛りが再現された．本手法も従来手法と同様に学習データとしては母語話者音声のみを用いており，訛りに頑健な音声認識を母語話者音声コーパスのみで実現するためのデータ拡張などへの応用が期待される．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"7","bibliographic_titles":[{"bibliographic_title":"研究報告音声言語情報処理（SLP）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2024-12-05","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"22","bibliographicVolumeNumber":"2024-SLP-154"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":241642,"links":{}}