{"updated":"2025-01-20T05:53:04.906746+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00176407","sets":["1164:5159:8497:9012"]},"path":["9012"],"owner":"11","recid":"176407","title":["DNNに基づくテキスト音声合成のためのFFTスペクトルを用いた位相復元に基づく音声波形生成"],"pubdate":{"attribute_name":"公開日","attribute_value":"2016-12-13"},"_buckets":{"deposit":"2c0e0469-3f17-4663-9eb5-6d5e92468db1"},"_deposit":{"id":"176407","pid":{"type":"depid","value":"176407","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"DNNに基づくテキスト音声合成のためのFFTスペクトルを用いた位相復元に基づく音声波形生成","author_link":["371139","371142","371140","371141"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"DNNに基づくテキスト音声合成のためのFFTスペクトルを用いた位相復元に基づく音声波形生成"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"音声合成","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2016-12-13","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"国立情報学研究所"},{"subitem_text_value":"Naver Labs, Naver Corporation"},{"subitem_text_value":"日本電信電話株式会社NTTコミュニケーション科学基礎研究所"},{"subitem_text_value":"国立情報学研究所"}]},"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/176407/files/IPSJ-SLP16114021.pdf","label":"IPSJ-SLP16114021.pdf"},"date":[{"dateType":"Available","dateValue":"2018-12-13"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP16114021.pdf","filesize":[{"value":"1.9 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":"12d83486-6f57-4f15-a7e7-d2894a6e63b4","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2016 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"高木, 信二"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Sangjin, Kim"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"亀岡, 弘和"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"山岸, 順一"}],"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":"多くの統計的パラメトリック音声合成システムでは，高品質ボコーダを用い，音声波形を構築する．その際，ソース ・ フィルタモデルに基づくボコーダが利用されることが多く，言語特徴量からメルケプストラム，F0 といった音響特徴量を予測し，ボコーダによる音声波形生成が行われる．しかし，ボコーダを用いたことに起因する合成音声の自然性の低下が常に問題となっており，これまで様々な研究が報告されている．しかし，ソース ・ フィルタモデルに基づいている限り，この問題を完全に解決することは容易ではない．そこで本研究では，ボコーダを用いない音声合成システム構築することを考える．具体的には，統計的パラメトリック音声合成において，振幅スペクトルからの位相復元，逆短時間フーリエ変換，および重加算法 (OLA) に基づき波形を生成することについて検討する．今回提案する音声合成の枠組みでは，まず，調波構造を含む振幅スペクトルの予測を DNN 音響モデルにより行い，次に，予測された振幅スペクトルから Griffin / Lim 法により位相を復元することで，音声波形の生成を行う．主観評価実験により，高品質ボコーダを用いた DNN 音声合成システムと提案システムの比較を行った結果，提案法ではボコーダに基づく合成音声特有のバジー感が無い合成音声の生成が可能であることを確認できた．","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":"2016-12-13","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"21","bibliographicVolumeNumber":"2016-SLP-114"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"created":"2025-01-19T00:46:03.405747+00:00","id":176407,"links":{}}