{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00216850","sets":["1164:8666:10876:10877"]},"path":["10877"],"owner":"44499","recid":"216850","title":["健常音声からの声質変換と多数話者ボコーダによる構音障害話者の明瞭な音声合成の検討"],"pubdate":{"attribute_name":"公開日","attribute_value":"2022-03-01"},"_buckets":{"deposit":"cb85f4d0-455e-42c3-a412-ad1ceeeaaec7"},"_deposit":{"id":"216850","pid":{"type":"depid","value":"216850","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"健常音声からの声質変換と多数話者ボコーダによる構音障害話者の明瞭な音声合成の検討","author_link":["560625","560623","560626","560624","560622","560619","560621","560620"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"健常音声からの声質変換と多数話者ボコーダによる構音障害話者の明瞭な音声合成の検討"},{"subitem_title":"A study on high-intelligibility speech synthesis of dysarthric speakers using voice conversion from normal speech and multi-speaker vocoder","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"聴覚・言語障害支援(1)","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2022-03-01","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"株式会社ヒューマンテクノシステム"},{"subitem_text_value":"東北大学大学院工学研究科"},{"subitem_text_value":"東北大学大学院工学研究科"},{"subitem_text_value":"株式会社ヒューマンテクノシステム"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Human Techno System Co., Ltd.","subitem_text_language":"en"},{"subitem_text_value":"Tohoku University","subitem_text_language":"en"},{"subitem_text_value":"Tohoku University","subitem_text_language":"en"},{"subitem_text_value":"Human Techno System Co., Ltd.","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/216850/files/IPSJ-AAC22018004.pdf","label":"IPSJ-AAC22018004.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-AAC22018004.pdf","filesize":[{"value":"4.0 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"52"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"6b9a58a6-d046-483b-b1aa-478ed0327879","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2022 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":"高野, 哲朗"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"能勢, 隆"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"金垣, 葵"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"渡辺, 聡"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Tetsuro, Takano","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Takashi, Nose","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Aoi, Kanagaki","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Satoshi, Watanabe","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA12752949","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":"2432-2431","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"健常話者の音声から構音障害話者の音声へと声質変換することにより，障害話者の声色を維持しつつ聞き取りやすい合成音声を生成する検討を行った．少量の障害話者データであっても鮮明な音声が得られる多数話者ボコーダを利用し，話速変換による本人性の向上や，音高拡張による抑揚の単調性の解消，ファインチューニングによる単語データのみの学習でその有効性を示した．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"In this study, we investigated the possibility of generating intelligible synthetic speech by converting the voice of a normal speaker to that of a dysarthric speaker while maintaining the tone of the speaker’s voice. Using a multi-speaker vocoder which can produce clear synthetic voice even with a small amount of impaired speaker data, we demonstrated the effectiveness of speech rate conversion to improve voice similarity, pitch augmentation to overcome monotonicity of intonation, and fine tuning to learn with word data.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告アクセシビリティ（AAC）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2022-03-01","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"4","bibliographicVolumeNumber":"2022-AAC-18"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":216850,"updated":"2025-01-19T15:42:46.470208+00:00","links":{},"created":"2025-01-19T01:17:21.821700+00:00"}