{"created":"2025-01-19T01:17:08.696590+00:00","updated":"2025-01-19T15:47:28.723584+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00216621","sets":["1164:5159:10869:10870"]},"path":["10870"],"owner":"44499","recid":"216621","title":["アクセント潜在変数を用いた方言音声合成における文単位生成の評価"],"pubdate":{"attribute_name":"公開日","attribute_value":"2022-02-22"},"_buckets":{"deposit":"7c756b12-2e06-40f4-a27d-fc353589cd0a"},"_deposit":{"id":"216621","pid":{"type":"depid","value":"216621","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"アクセント潜在変数を用いた方言音声合成における文単位生成の評価","author_link":["559329","559330","559332","559334","559328","559327","559333","559331"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"アクセント潜在変数を用いた方言音声合成における文単位生成の評価"},{"subitem_title":"Evaluation of sentence-level generation in Japanese dialect speech synthesis using accent latent variables","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"SP2 ","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2022-02-22","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東京大学大学院情報理工学系研究科"},{"subitem_text_value":"東京大学大学院情報理工学系研究科"},{"subitem_text_value":"東京大学大学院情報理工学系研究科"},{"subitem_text_value":"東京大学大学院情報理工学系研究科"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Information Science and Technology, the University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Science and Technology, the University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Science and Technology, the University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Science and Technology, the University of Tokyo","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/216621/files/IPSJ-SLP22140020.pdf","label":"IPSJ-SLP22140020.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP22140020.pdf","filesize":[{"value":"2.1 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"22"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"c50579b8-3994-4b6b-afb5-70d17f1b6e29","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":"湯舟, 航耶"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"郡山, 知樹"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"高道, 慎之介"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"猿渡, 洋"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Kazuya, Yufune","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Tomoki, Koriyama","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shinnosuke, Takamichi","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hiroshi, Saruwatari","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":"日本語方言音声合成は個人化された音声合成システムなどにとって有用であるが，アクセントラベルを用意できないことが合成音声の自然性を高める上での障害となっている．著者らは過去，アクセントラベルなしで日本 語方言のピッチアクセントを生成するため，vector quantized variational autoencoder (VQ-VAE) を用いて方言ピッチアクセントをモーラ単位のアクセント潜在変数としてモデル化する手法を提案し，フレーズ単位の発話に対して評価を行った．これに続き本稿では，修正した同様の手法を文単位の方言発話に適用し，その評価を行う．実験では， 文単位発話に対してもアクセント潜在変数によって音声のピッチアクセントをモデル化できること，単語分割の精度 が高い場合に提案法は従来法よりも自然なピッチアクセントをテキストから生成できること，提案法によって生成されるピッチアクセントの可制御性が向上することを示す．","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":"2022-02-22","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"20","bibliographicVolumeNumber":"2022-SLP-140"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":216621,"links":{}}