{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00057023","sets":["1164:5159:5180:5185"]},"path":["5185"],"owner":"1","recid":"57023","title":["バイモーダル車内音声認識評価用データベースの構築"],"pubdate":{"attribute_name":"公開日","attribute_value":"2005-02-04"},"_buckets":{"deposit":"ab97e279-cd91-4256-bf49-ddef396d8de7"},"_deposit":{"id":"57023","pid":{"type":"depid","value":"57023","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"バイモーダル車内音声認識評価用データベースの構築","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"バイモーダル車内音声認識評価用データベースの構築"},{"subitem_title":"Construction of Bimodal Database for Evaluating In-Car Speech Recognition","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2005-02-04","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"名古屋大学大学院情報科学研究科"},{"subitem_text_value":"名古屋大学大学院情報科学研究科"},{"subitem_text_value":"名古屋大学大学院情報科学研究科"},{"subitem_text_value":"名古屋大学大学院情報科学研究科"},{"subitem_text_value":"名古屋大学大学院情報科学研究科"},{"subitem_text_value":"名古屋大学大学院情報科学研究科"},{"subitem_text_value":"名古屋大学大学院情報科学研究科"},{"subitem_text_value":"名古屋大学大学院情報科学研究科"},{"subitem_text_value":"名城大学理工学部情報工学科"},{"subitem_text_value":"名古屋商科大学経営情報学部"},{"subitem_text_value":"（株）豊田中央研究所"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Information Science, Nagoya University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Science, Nagoya University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Science, Nagoya University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Science, Nagoya University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Science, Nagoya University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Science, Nagoya University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Science, Nagoya University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Science, Nagoya University","subitem_text_language":"en"},{"subitem_text_value":"Department of Information Engineering, Faculty of Science and Technology, Meijo University","subitem_text_language":"en"},{"subitem_text_value":"Faculty of Management Information Science, Nagoya University of Commerce & Business","subitem_text_language":"en"},{"subitem_text_value":"Toyota Central R&D Lab., Inc.","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/57023/files/IPSJ-SLP04055007.pdf"},"date":[{"dateType":"Available","dateValue":"2007-02-04"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP04055007.pdf","filesize":[{"value":"876.3 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":"bcc80d86-ee34-471c-8936-003c626aaf3f","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2005 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"根木, 大輔"},{"creatorName":"前野, 俊希"},{"creatorName":"北坂, 孝幸"},{"creatorName":"森, 健策"},{"creatorName":"末永, 康仁"},{"creatorName":"宮島, 千代美"},{"creatorName":"伊藤, 克亘"},{"creatorName":"武田, 一哉"},{"creatorName":"板倉, 文忠"},{"creatorName":"佐野, 昌己"},{"creatorName":"二宮, 芳樹"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Daisuke, NEGI","creatorNameLang":"en"},{"creatorName":"Toshiki, MAENO","creatorNameLang":"en"},{"creatorName":"Takayuki, KITASAKA","creatorNameLang":"en"},{"creatorName":"Kensaku, MORI","creatorNameLang":"en"},{"creatorName":"Yasuhito, SUENAGA","creatorNameLang":"en"},{"creatorName":"Chiyomi, MIYAJIMA","creatorNameLang":"en"},{"creatorName":"Katsunobu, ITOU","creatorNameLang":"en"},{"creatorName":"Kazuya, TAKEDA","creatorNameLang":"en"},{"creatorName":"Fumitada, ITAKURA","creatorNameLang":"en"},{"creatorName":"Masami, SANO","creatorNameLang":"en"},{"creatorName":"Yoshiki, NINOMIYA","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":"近年，現実の雑音環境下の様々なシーンにおいて音声認識率を向上させるために，音声情報と映像情報を統合したバイモーダル音声認識への関心が高まっている．映像情報は音響雑音の影響を受けない情報源として，音声認識において重要な役割を果たすものと考えられる．しかし，大規模バイモーダルデータベースが少ないことなどから，映像情報は実際の音声認識システムにおいて十分に利用されるには至っていない．そこで我々は，これまでに構築されている雑音環境下音声認識評価用共通データベースAURORA-2J/AURORA-3Jの仕様に則り，高品質カラー映像と近赤外映像を付加して収録を行い，新しいデータベースAURORA-2J-AV（室内），AURORA-3J-AV（自動車内）を構築している．本稿ではこれらのデータベースの詳細について述べる．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"There are remarkable interests on bimodal speech recognition, which integrate audio and visual information, to improve speech recognition rates. Visual information plays a very important role in speech recognition since it is not affected by acoustic noises. However, such kind of information has not been fully used in existing actual speech recognition systems because  of the lack of large-scale bimodal databases. Therefore we are building new databases called AURORA-2J-AV(indoor) and AURORA-3J-AV(in-vehicle) that contain aural signals and high quality facial images taken by color and near-infrared cameras. The utterance tasks of these databases are the same as those of our AURORA-2J/AURORA-3J database for evaluating speech recognition method under noisy environments. This paper describes the detailed specification of the databases.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"40","bibliographic_titles":[{"bibliographic_title":"情報処理学会研究報告音声言語情報処理（SLP）"}],"bibliographicPageStart":"35","bibliographicIssueDates":{"bibliographicIssueDate":"2005-02-04","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"12(2004-SLP-055)","bibliographicVolumeNumber":"2005"}]},"relation_version_is_last":true,"weko_creator_id":"1"},"id":57023,"updated":"2025-01-22T04:41:36.028608+00:00","links":{},"created":"2025-01-18T23:20:18.804334+00:00"}