{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00197795","sets":["1164:5064:9706:9832"]},"path":["9832"],"owner":"44499","recid":"197795","title":["音声合成のための信号処理・統計モデル"],"pubdate":{"attribute_name":"公開日","attribute_value":"2019-06-15"},"_buckets":{"deposit":"03b260b9-96f3-4a32-96ee-478edf5c5967"},"_deposit":{"id":"197795","pid":{"type":"depid","value":"197795","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"音声合成のための信号処理・統計モデル","author_link":["475302"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"音声合成のための信号処理・統計モデル"},{"subitem_title":"An overview of technology for speech synthesis","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"チュートリアル講演","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2019-06-15","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"ヤマハ株式会社"}]},"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/197795/files/IPSJ-MUS19123010.pdf","label":"IPSJ-MUS19123010.pdf"},"date":[{"dateType":"Available","dateValue":"2021-06-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-MUS19123010.pdf","filesize":[{"value":"95.2 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"5"},{"tax":["include_tax"],"price":"0","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"21"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"465dc2c3-f39f-4b37-a774-53574826659c","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2019 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"才野, 慶二郎"}],"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_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8752","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"本チュートリアルでは，テキスト音声合成のタスクに用いられる主要な技術について概観する．テキスト音声合成タスクは典型的には (1) テキストから言語特徴量を得る，(2) 言語特徴量から音響特徴量を得る，(3) 音響特徴量から波形を得る，という 3 つの部分問題で構成される．中でも特に盛んに取り組まれているのが (2) と (3) である．(2) では，かつては音声素片を選択的に使用する単位選択型手法が主流であった一方で，近年は統計モデルを使用して尤もらしい音響特徴量を推論する統計的パラメトリック手法がよく用いられる．(3) ではボコーダと呼ばれる決定論的な信号処理手法が広く用いられるとともに，近年ではディープニューラルネットワークに直接波形を生成させる手法も用いられはじめている．また (1) と (2) を 1 つのモデルで一気に解くような End-to-end を指向した深層学習手法も近年提案され，注目を集めている．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"1","bibliographic_titles":[{"bibliographic_title":"研究報告音楽情報科学（MUS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2019-06-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"10","bibliographicVolumeNumber":"2019-MUS-123"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":197795,"updated":"2025-01-19T22:12:24.686403+00:00","links":{},"created":"2025-01-19T01:02:12.967562+00:00"}