{"updated":"2025-01-21T13:10:53.520052+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00096756","sets":["1164:5159:7047:7342"]},"path":["7342"],"owner":"11","recid":"96756","title":["HMM音声合成技術の歌唱スタイル生成Job Pluginへの応用"],"pubdate":{"attribute_name":"公開日","attribute_value":"2013-12-12"},"_buckets":{"deposit":"c679fa67-cc6a-414b-8cbb-397efec8a0d7"},"_deposit":{"id":"96756","pid":{"type":"depid","value":"96756","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"HMM音声合成技術の歌唱スタイル生成Job Pluginへの応用","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"HMM音声合成技術の歌唱スタイル生成Job Pluginへの応用"},{"subitem_title":"Application of HMM-Based Speech Synthesis Techniques to a Singing Style Synthesis Job Plugin","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2013-12-12","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"ヤマハ株式会社研究開発統括部第１研究開発部音声グループ"},{"subitem_text_value":"ヤマハ株式会社研究開発統括部第１研究開発部音声グループ"},{"subitem_text_value":"ヤマハ株式会社研究開発統括部第１研究開発部音声グループ"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Speech Technology Group, Development Department 1, Research & Development Division, Yamaha Corporation","subitem_text_language":"en"},{"subitem_text_value":"Speech Technology Group, Development Department 1, Research & Development Division, Yamaha Corporation","subitem_text_language":"en"},{"subitem_text_value":"Speech Technology Group, Development Department 1, Research & Development Division, Yamaha Corporation","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/96756/files/IPSJ-SLP13099022.pdf"},"date":[{"dateType":"Available","dateValue":"2100-01-01"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP13099022.pdf","filesize":[{"value":"717.9 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"22"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"bf2299a7-c0ef-43f7-888b-b27f674a705e","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2013 by the Institute of Electronics, Information and Communication Engineers\nThis 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":"橘, 誠"},{"creatorName":"才野, 慶二郎"},{"creatorName":"久湊, 裕司"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Makoto, Tachibana","creatorNameLang":"en"},{"creatorName":"Keijiro, Saino","creatorNameLang":"en"},{"creatorName":"Yuji, Hisaminato","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_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"HMM 音声合成は統計的な韻律のモデル化により，話者性やスタイルを柔軟に多様化することができる．本稿では，その表現力を波形素片接続型の歌声合成システムである VOCALOID™ に取り入れる方法として，歌唱表現が現れる重要な特徴と考えられるピッチの変化をHMMでモデル化，生成する歌唱スタイル生成手法を提案する．HMM音声合成手法を歌唱スタイルのモデル化に利用する際には，未知の音高に対しても適切なパラメータ生成を行う必要がある．そこで本研究ではピッチベンドチェンジを用いたモデル化を提案する．また，長い時間伸ばされる音符に対して自然な変動を付与するため，ノート内を複数のセグメントに分割した単位でモデル化し，多段階のコンテキストクラスタリングを導入して楽曲構造と音符内の変動を階層的に表現する．また，この手法をVOCALOID™3の機能である Job Plugin として組み込んだ例を紹介する．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Recent HMM-based speech synthesis systems have the capability to control speaker/style characteristics by statistically modeling prosodic features of speech. In this paper, we aim to introduce such flexibility into VOCALOID™, a singing voice synthesizer based on concatenative synthesis. An HMM is used to model the pitch trajectory, which is an important feature for expressing singing style. In order to synthesize appropriate results for pitches which do not have training data, we propose using pitch bend change as a feature for training the HMM. We also propose a segment-level unit modeling and multiple-stage clustering technique for the expression of long note sequences. We show the proposed technique implemented as a VOCALOID™3 Job Plugin.","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":"2013-12-12","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"22","bibliographicVolumeNumber":"2013-SLP-99"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"created":"2025-01-18T23:43:29.810352+00:00","id":96756,"links":{}}