{"created":"2025-01-19T01:46:22.667808+00:00","updated":"2025-01-19T07:35:30.895494+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00241649","sets":["1164:5159:11541:11870"]},"path":["11870"],"owner":"44499","recid":"241649","title":["画像ベース中間表現を用いた多言語音声翻訳システムの提案と評価"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-12-05"},"_buckets":{"deposit":"cb22f28d-683b-4842-b709-622bf891ee5c"},"_deposit":{"id":"241649","pid":{"type":"depid","value":"241649","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"画像ベース中間表現を用いた多言語音声翻訳システムの提案と評価","author_link":["665649","665648","665647","665650"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"画像ベース中間表現を用いた多言語音声翻訳システムの提案と評価"},{"subitem_title":"Proposal and Evaluation of a Multilingual Speech-to-Speech Translation System Using Image-Based Intermediate Representations","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"特別セッション：分野横断","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2024-12-05","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"明星大学大学院理工学研究科"},{"subitem_text_value":"明星大学大学院理工学研究科"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"The Graduate School of Science and Technology, Meisei University","subitem_text_language":"en"},{"subitem_text_value":"The Graduate School of Science and Technology, Meisei University","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/241649/files/IPSJ-SLP24154029.pdf","label":"IPSJ-SLP24154029.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP24154029.pdf","filesize":[{"value":"3.4 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"22"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"c5f00dc9-e287-466f-b682-8f41c9fa10da","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Institute of Electronics, Information and Communication Engineers This SIG report is only available to those in membership of the SIG."}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"趙, 澤毅"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"林, 実"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Takui, Cho","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Minoru, Hayashi","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":"本研究では，多言語音声翻訳におけるモジュール数増加の課題を解決するため，画像を中間表現とする新たな手法を提案する．従来の言語ペアごとのモジュールを用いた翻訳ではなく，画像を言語間の橋渡しとして利用し，音声から画像，画像から音声への相互変換を通じて，多言語間の直接音声翻訳を可能にした．評価実験の結果，視覚的特徴を用いた中間表現が，多言語音声翻訳プロセスにおけるモジュール数の削減に寄与することが示された．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"This study proposes a novel approach that uses images as intermediate representations to address the challenge of increasing module numbers in multilingual speech-to-speech translation. Rather than relying on language-pair-specific modules, the proposed method enables direct multilingual translation by using images as a bridge between languages, allowing for conversions from speech to images and images to speech. Experimental evaluations demonstrate that using image-based intermediate representations with visual features effectively reduces the number of modules required in the multilingual speech translation process.","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":"2024-12-05","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"29","bibliographicVolumeNumber":"2024-SLP-154"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":241649,"links":{}}