{"links":{},"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00056885","sets":["1164:5159:5174:5177"]},"path":["5177"],"owner":"1","recid":"56885","title":["LPC残差のキュムラントとオンラインEMアルゴリズムに基づいた頑健な発話区間検出"],"pubdate":{"attribute_name":"公開日","attribute_value":"2006-07-07"},"_buckets":{"deposit":"030cf4fc-6fb8-4088-8997-d23bbb6bd297"},"_deposit":{"id":"56885","pid":{"type":"depid","value":"56885","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"LPC残差のキュムラントとオンラインEMアルゴリズムに基づいた頑健な発話区間検出","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"LPC残差のキュムラントとオンラインEMアルゴリズムに基づいた頑健な発話区間検出"},{"subitem_title":"Robust Voice Activity Detection Based on Enhanced Cumulant of LPC Residual and On-line EM Algorithm","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2006-07-07","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"京都大学　情報学研究科 知能情報学専攻"},{"subitem_text_value":"京都大学　情報学研究科 知能情報学専攻"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"School of Informatics, Kyoto University","subitem_text_language":"en"},{"subitem_text_value":"School of Informatics, Kyoto University","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/56885/files/IPSJ-SLP06062003.pdf"},"date":[{"dateType":"Available","dateValue":"2008-07-07"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP06062003.pdf","filesize":[{"value":"288.1 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":"1fc30df6-6ad2-4140-bbd0-6b9f28afc8df","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2006 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"クーナポダビド"},{"creatorName":"河原, 達也"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"David, Cournapeau","creatorNameLang":"en"},{"creatorName":"Tatsuya, Kawahara","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":"人間どうしの会話のマルチモーダルなセンシングやアノテーションを指向して、雑音下において頑健に発話区間を検出する方法を提案する。本手法は、LPC残差の高次統計量と自己相関関数を組み合わせた特徴量に基づいており、オンライン版のEMアルゴリズムによって学習・分類を行う。展示会場においてウェアラブルデバイスによって集められた会話データに対して評価を行った結果、(1)提案する特徴量によって、背景発話などに対して頑健に検出できること、(2)オンラインEMアルゴリズムによって、リアルタイムに学習・適応が可能なこと、がわかった。提案する特徴量は、計算量も小さく、処理遅延も少ない。","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"This paper addresses the problem of segmenting audio data recorded with embedded devices for the purpose of intelligent sensing in the context of multi-modal interactions.We propose a real-time method for robust speech detection in natural, noisy environments. It is based on a fusion of high order statistics of the LPC residual and autocorrelation, and adopts an on-line version of Expectation Maximization algorithm for the classification. Experimental evaluations show that the proposed method provides better detection performance under different types of natural noises, working robustly against other voices in the context of multi-speaker interactive situations. As the proposed method is based on features which have a low computational cost, and has a small latency, it is suitable for real-time tracking applications.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"18","bibliographic_titles":[{"bibliographic_title":"情報処理学会研究報告音声言語情報処理（SLP）"}],"bibliographicPageStart":"13","bibliographicIssueDates":{"bibliographicIssueDate":"2006-07-07","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"73(2006-SLP-062)","bibliographicVolumeNumber":"2006"}]},"relation_version_is_last":true,"weko_creator_id":"1"},"updated":"2025-01-22T04:45:37.969585+00:00","created":"2025-01-18T23:20:12.259118+00:00","id":56885}