{"updated":"2025-01-22T07:40:07.860840+00:00","links":{},"id":50380,"created":"2025-01-18T23:15:10.312912+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00050380","sets":["1164:4402:4422:4426"]},"path":["4426"],"owner":"1","recid":"50380","title":["統計的手法に基づいた画像・音声情報からの概念獲得"],"pubdate":{"attribute_name":"公開日","attribute_value":"2004-03-17"},"_buckets":{"deposit":"a9c75102-d411-4c0e-834b-f820f2fa0ba5"},"_deposit":{"id":"50380","pid":{"type":"depid","value":"50380","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"統計的手法に基づいた画像・音声情報からの概念獲得","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"統計的手法に基づいた画像・音声情報からの概念獲得"},{"subitem_title":"The Concept of Linguistic Symbol acquisition from Image and Speech based on statistical technique","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2004-03-17","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"武蔵工業大学"},{"subitem_text_value":"武蔵工業大学"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Musashi Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Musashi Institute of Technology","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/50380/files/IPSJ-ICS03135034.pdf"},"date":[{"dateType":"Available","dateValue":"2006-03-17"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-ICS03135034.pdf","filesize":[{"value":"1.0 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":"25"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"ad9fd92e-6eaa-4e3a-a554-62e9e77d8473","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2004 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"長島, 徹"},{"creatorName":"荒井, 秀一"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Tohru, Nagashima","creatorNameLang":"en"},{"creatorName":"Shuichi, Arai","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11135936","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":"これまでのメディア認識・理解の研究の多くは，シンボルを用いてより複雑なシンボルの学習，シンボル間の関係学習などを行っていた．しかし，実環境において計算機が人間の提示する情報を理解するためには，言葉の意味そのものを前もって獲得している必要がある．そこで，我々はシンボリック処理を用いずに画像・音声刺激という実メディアから，言葉の意味そのものである言語シンボル概念を獲得する枠組みを提案してきた．しかし，画像・音声といった異なったメディア情報を扱うため，それぞれの認識結果の尺度が異なっており，直接的な比較を行うためには，何らかの変換が必要となる．そこで，本研究では画像・音声メディアの認識結果を統計的な手法を用いて，保持している知識と入力情報の適合確率として表現する手法を提案し，適合確率を用いたモデル化を行う．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Former research of media recognition and an understanding learned the complicated symbol and The relation between symbols using symbol. However, the computer needs to acquire sense of language for understands information which man presents in the real world. So, we proposed a framework that acquires the concept of linguistic symbol from image and voice medelia not using symbolic processing. It is necessary to male the measure of the result of recognition of some media the same for comparison. inthis paper, we propose a method to translate the probability of conformity of knowledge and input based on statistical technique from the image and voice media and a framework using it.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"198","bibliographic_titles":[{"bibliographic_title":"情報処理学会研究報告知能と複雑系（ICS）"}],"bibliographicPageStart":"193","bibliographicIssueDates":{"bibliographicIssueDate":"2004-03-17","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"29(2003-ICS-135)","bibliographicVolumeNumber":"2004"}]},"relation_version_is_last":true,"weko_creator_id":"1"}}