{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00234701","sets":["1164:5159:11541:11627"]},"path":["11627"],"owner":"44499","recid":"234701","title":["離散音声トークン生成によるテキスト音声合成のための音声主観評価値予測に基づくdecoding戦略"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-06-07"},"_buckets":{"deposit":"1871754e-c9d3-4857-bcc8-8013be16270e"},"_deposit":{"id":"234701","pid":{"type":"depid","value":"234701","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"離散音声トークン生成によるテキスト音声合成のための音声主観評価値予測に基づくdecoding戦略","author_link":["639897","639899","639900","639895","639898","639896","639894","639901"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"離散音声トークン生成によるテキスト音声合成のための音声主観評価値予測に基づくdecoding戦略"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"ポスターセッション1","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2024-06-07","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東京大学"},{"subitem_text_value":"東京大学"},{"subitem_text_value":"東京大学"},{"subitem_text_value":"東京大学"}]},"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/234701/files/IPSJ-SLP24152014.pdf","label":"IPSJ-SLP24152014.pdf"},"date":[{"dateType":"Available","dateValue":"2026-06-07"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP24152014.pdf","filesize":[{"value":"1.1 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":"2ab75fb1-7855-47e2-8123-0404f5724f2f","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"山内, 一輝"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"中田, 亘"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"齋藤, 佑樹"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"猿渡, 洋"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Kazuki, Yamauchi","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Wataru, Nakata","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yuki, Saito","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hiroshi, Saruwatari","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_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":"本論文では，離散音声トークン生成に基づくテキスト音声合成モデルおける decoding 戦略について探求する．我々は，テキスト生成における嗜好データに基づく decoding 戦略に着想を得た，離散音声トークン生成に向けた主観評価値予測に基づく新たな decoding 戦略を提案する．主観評価実験により，提案手法が合成音声の degeneration 問題を回避し，自然性を向上させるのに有効であることを示す．提案手法はモジュール性および拡張性が高く，音声合成モデルをアライメントするための有望なアプローチである．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告音声言語情報処理（SLP）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2024-06-07","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"14","bibliographicVolumeNumber":"2024-SLP-152"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":234701,"updated":"2025-01-19T09:43:13.798460+00:00","links":{},"created":"2025-01-19T01:36:34.701751+00:00"}