{"updated":"2025-01-23T02:31:09.560033+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00010937","sets":["581:638:648"]},"path":["648"],"owner":"1","recid":"10937","title":["隠れマルコフモデルに基づいた歌声合成システム"],"pubdate":{"attribute_name":"公開日","attribute_value":"2004-03-15"},"_buckets":{"deposit":"00b708f4-0337-4bcb-a747-7cc20c25f384"},"_deposit":{"id":"10937","pid":{"type":"depid","value":"10937","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"隠れマルコフモデルに基づいた歌声合成システム","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"隠れマルコフモデルに基づいた歌声合成システム"},{"subitem_title":"A Singing Voice Synthesis System Based on Hidden Markov Model","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"特集：音楽情報科学","subitem_subject_scheme":"Other"}]},"item_type_id":"2","publish_date":"2004-03-15","item_2_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"名古屋工業大学大学院工学研究科"},{"subitem_text_value":"名古屋工業大学大学院工学研究科"},{"subitem_text_value":"名古屋工業大学大学院工学研究科"},{"subitem_text_value":"名古屋工業大学大学院工学研究科"}]},"item_2_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Department of Computer Science and Engineering, Nagoya Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Department of Computer Science and Engineering, Nagoya Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Department of Computer Science and Engineering, Nagoya Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Department of Computer Science and Engineering, Nagoya Institute of Technology","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"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/10937/files/IPSJ-JNL4503007.pdf"},"date":[{"dateType":"Available","dateValue":"2006-03-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-JNL4503007.pdf","filesize":[{"value":"274.2 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":"8"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"6f69ffd2-a5d3-4c39-bd7a-755eab69aa34","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2004 by the Information Processing Society of Japan"}]},"item_2_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"酒向慎司"},{"creatorName":"宮島千代美;徳田恵一"},{"creatorName":"北村正"}],"nameIdentifiers":[{}]}]},"item_2_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Shinji, Sako;ChiyomiMiyajima;KeiichiTokuda;TadashiKitamura","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_2_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00116647","subitem_source_identifier_type":"NCID"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_6501","resourcetype":"journal article"}]},"item_2_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"1882-7764","subitem_source_identifier_type":"ISSN"}]},"item_2_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"隠れマルコフモデルに基づく音声合成方式を歌声合成に拡張することにより構築した歌声合成システムについて述べる．本システムでは，歌い手の声の質と基本周波数パターンに関する特徴をモデル化するため，スペクトルと基本周波数パターンをHMMにより同時にモデル化している．特に，自然な歌声を合成するうえで重要な要素となる音符の音階や音長の基本周波数パターンへの影響を精度良くモデル化するため，楽譜から得られる音階と音長を考慮したコンテキスト依存モデルを構築している．これらのモデルに対して決定木によるコンテキストクラスタリングを行うことで，未知の楽曲からの歌声合成が可能となっている．実験から，歌い手の特徴を再現し歌声の合成が可能であることを示す．","subitem_description_type":"Other"}]},"item_2_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"We describe a singing voice synthesis system by applying HMM-basedspeech synthesis technique.In this system, a sequence of spectrum and F0 are modeledsimultaneously in a unified framework of HMM, and context dependentHMMs are constructed by taking account of contextual factors thataffects singing voice.In addition, the distributions for spectral and F0 parameter areclustered independently by using a decision-tree based contextclustering technique.Synthetic singing voice is generated from HMMs themselves by usingparameter generation algorithm. In the experiments, we confirmed that smooth and natural-soundingsinging voice is synthesised. It is also maintains the characteristicsand personality of the donor of the singing voice data for HMMtraining.","subitem_description_type":"Other"}]},"item_2_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"727","bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌"}],"bibliographicPageStart":"719","bibliographicIssueDates":{"bibliographicIssueDate":"2004-03-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"3","bibliographicVolumeNumber":"45"}]},"relation_version_is_last":true,"weko_creator_id":"1"},"created":"2025-01-18T22:45:42.550601+00:00","id":10937,"links":{}}