{"created":"2025-01-19T01:33:22.244429+00:00","updated":"2025-01-19T10:26:04.239885+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00232479","sets":["1164:5159:11541:11549"]},"path":["11549"],"owner":"44499","recid":"232479","title":["音環境に適応するテキスト音声合成のための一人称視点コーパス構築"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-02-22"},"_buckets":{"deposit":"f39bd7f2-b592-4fcd-9300-24dee899b595"},"_deposit":{"id":"232479","pid":{"type":"depid","value":"232479","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"音環境に適応するテキスト音声合成のための一人称視点コーパス構築","author_link":["629323","629325","629324","629326","629327"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"音環境に適応するテキスト音声合成のための一人称視点コーパス構築"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"SLP","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2024-02-22","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":"産業技術総合研究所"},{"subitem_text_value":"東京大学"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"National Institute of Advanced Industrial Science and Technology (AIST)","subitem_text_language":"en"},{"subitem_text_value":"The University of Tokyo","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/232479/files/IPSJ-SLP24151009.pdf","label":"IPSJ-SLP24151009.pdf"},"date":[{"dateType":"Available","dateValue":"2026-02-22"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP24151009.pdf","filesize":[{"value":"2.3 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":"4f36e143-14fb-4cf1-96ba-d11945741acd","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":"武, 伯寒"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"高道, 慎之介"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"関, 健太郎"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"坂東, 宜昭"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"猿渡, 洋"}],"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":"テキスト音声合成 (text-to-speech，TTS) モデルが環境雑音や対話相手の発話といった聴取者の音環境を考慮することは，多様な音環境に適応して自然な対話を行う対話ロボットなどへの応用に必要である．本研究では音環境に適応できる TTS モデルを構築を目指す．まず，話者の発話音声・受聴音・一人称視点映像を時刻同期して収録する自発対話コーパスを構築した．次に構築したコーパスを用いて学習した TTS モデルと比較実験により，TTS モデルにおける音環境を考慮する機構の必要性について検討した．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"9","bibliographic_titles":[{"bibliographic_title":"研究報告音声言語情報処理（SLP）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2024-02-22","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"9","bibliographicVolumeNumber":"2024-SLP-151"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":232479,"links":{}}