{"id":67638,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00067638","sets":["1164:5159:6009:6012"]},"path":["6012"],"owner":"10","recid":"67638","title":["音声合成を用いたインターネット動画用音声ガイド"],"pubdate":{"attribute_name":"公開日","attribute_value":"2010-02-05"},"_buckets":{"deposit":"0a0d9023-8d72-4948-8be8-a40ef98f6099"},"_deposit":{"id":"67638","pid":{"type":"depid","value":"67638","revision_id":0},"owners":[10],"status":"published","created_by":10},"item_title":"音声合成を用いたインターネット動画用音声ガイド","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"音声合成を用いたインターネット動画用音声ガイド"},{"subitem_title":"TTS to Provide Audio Descriptions of Internet Videos","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"マルチメディア，マルチモーダル","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2010-02-05","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"日本ＩＢＭ東京基礎研究所"},{"subitem_text_value":"日本ＩＢＭ東京基礎研究所"},{"subitem_text_value":"日本ＩＢＭ東京基礎研究所"},{"subitem_text_value":"日本ＩＢＭ東京基礎研究所"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"IBM Research - Tokyo","subitem_text_language":"en"},{"subitem_text_value":"IBM Research - Tokyo","subitem_text_language":"en"},{"subitem_text_value":"IBM Research - Tokyo","subitem_text_language":"en"},{"subitem_text_value":"IBM Research - Tokyo","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"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/67638/files/IPSJ-SLP10080001.pdf"},"date":[{"dateType":"Available","dateValue":"2012-02-05"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP10080001.pdf","filesize":[{"value":"558.6 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":"22"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"b4834c1b-821c-4888-8745-dea402b76856","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2010 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"立花, 隆輝"},{"creatorName":"長野, 徹"},{"creatorName":"高木, 啓伸"},{"creatorName":"西村, 雅史"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Ryuki, Tachibana","creatorNameLang":"en"},{"creatorName":"Tohru, Nagano","creatorNameLang":"en"},{"creatorName":"Hironobu, Takagi","creatorNameLang":"en"},{"creatorName":"Masafumi, Nishimura","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_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"筆者らは、音声合成 (TTS) を用いてインターネット動画用の音声ガイド (AD) を作成・流通しやすくする枠組みを開発している。AD を TTS でどのように作成すればどれほど有用になるのかまだ明らかではなかった。AD 作成において、音声合成ならではの新しい表現方法、映画など感情表現を伴う動画での有用性、感情音声合成の効果なども興味深い疑問点である。本論文では、これらの疑問点に関してTTSを用いた AD の予備実験の結果を紹介する。そこでは、特にドラマに対して高品質な TTS の有効性が示唆された。そして、まもなく実施予定の本実験に向け準備中の感情音声合成についても実験結果を紹介する。TTS を利用することによって AD 作成の負担が軽減され、無数のボランティアが作成した多数の AD が利用可能になることが期待される。","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"We are developing a collaborative Web accessibility framework that facilitates the authoring and sharing of Audio Descriptions (AD) for Internet videos by using a Text-To-Speech (TTS) engine. The crucial aspects of TTS-generated ADs and their utility are still unknown. It is natural that two-hour romantic movies would require higher quality for TTS-generated ADs than are needed for short e-learning videos. In this paper, we introduce the results of preliminary experiments of TTS-generated ADs for two video genres. The results suggest that an AD generated with a high quality TTS system is feasible for dramas. We also present experimental results for expressive TTS systems. We believe that TTS-generated ADs reduce the authoring costs and will allow for widespread sharing of ADs created by large numbers of volunteers.","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":"2010-02-05","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2010-SLP-80"}]},"relation_version_is_last":true,"weko_creator_id":"10"},"updated":"2025-01-22T00:31:38.044862+00:00","created":"2025-01-18T23:27:58.534999+00:00","links":{}}