{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00113351","sets":["1164:5064:7900:7901"]},"path":["7901"],"owner":"11","recid":"113351","title":["HMM歌声合成における音声データの誤りに頑健なモデル化手法の検討"],"pubdate":{"attribute_name":"公開日","attribute_value":"2015-02-23"},"_buckets":{"deposit":"5a857b19-3e29-49ec-81f0-b40ddb0fd8b9"},"_deposit":{"id":"113351","pid":{"type":"depid","value":"113351","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"HMM歌声合成における音声データの誤りに頑健なモデル化手法の検討","author_link":["37961","37957","37956","37965","37966","37960","37958","37963","37962","37955","37964","37959"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"HMM歌声合成における音声データの誤りに頑健なモデル化手法の検討"},{"subitem_title":"A robust modeling technique against training data errors for HMM-based singing voice synthesis","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"歌声・歌唱分析","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2015-02-23","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"名古屋工業大学"},{"subitem_text_value":"名古屋工業大学"},{"subitem_text_value":"名古屋工業大学"},{"subitem_text_value":"名古屋工業大学"},{"subitem_text_value":"名古屋工業大学"},{"subitem_text_value":"名古屋工業大学"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Nagoya Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Nagoya Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Nagoya Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Nagoya Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Nagoya Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Nagoya Institute of Technology","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/113351/files/IPSJ-MUS15106013.pdf"},"date":[{"dateType":"Available","dateValue":"2017-02-23"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-MUS15106013.pdf","filesize":[{"value":"465.2 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"21"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"1a5caf88-e58f-4d62-8641-c206ac91250d","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2015 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"虫鹿, 弘二"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"中村, 和寛"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"橋本, 佳"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"大浦, 圭一郎"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"南角, 吉彦"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"徳田, 恵一"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Koji, Mushika","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Kazuhiro, Nakamura","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Kei, Hashimoto","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Keiichiro, Oura","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yoshihiko, Nankaku","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Keiichi, Tokuda","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10438388","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":"隠れマルコフモデル (HMM) に基づく歌声合成システムは，あらかじめ用意された歌声データから統計モデルを学習し，任意の歌声を合成する．HMM 歌声合成の性能は学習データに強く依存するため，高品質な歌声を合成するためには高品質な歌声データベースが必要になる．しかし，実際のデータベースには，歌い間違いやノイズなどの誤りが含まれていることが多い．特に，これからは音声合成の分野でも，インターネット上の大量のデータを学習に有効活用するという流れが加速していくと考えられ，そのような誤りを多く含むデータから高精度なモデルを学習する手法が必要である．そこで本稿では，学習データ内の誤りを局所的に除外することによる誤りに頑健なモデルの学習手法を提案し，主観評価実験により提案手法の有効性を評価する．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告音楽情報科学（MUS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2015-02-23","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"13","bibliographicVolumeNumber":"2015-MUS-106"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"updated":"2025-01-20T19:40:39.030059+00:00","created":"2025-01-18T23:54:57.212085+00:00","links":{},"id":113351}