{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00057231","sets":["1164:5159:5192:5195"]},"path":["5195"],"owner":"1","recid":"57231","title":["雑音下音声認識のための複数の前処理手法の統合とそのAURORA - 2Jによる評価"],"pubdate":{"attribute_name":"公開日","attribute_value":"2003-07-18"},"_buckets":{"deposit":"3618f61a-2a9f-44d5-b0fe-68238d143841"},"_deposit":{"id":"57231","pid":{"type":"depid","value":"57231","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"雑音下音声認識のための複数の前処理手法の統合とそのAURORA - 2Jによる評価","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"雑音下音声認識のための複数の前処理手法の統合とそのAURORA - 2Jによる評価"},{"subitem_title":"Integration of Noise Reduction Algorithms for AURORA - 2J Task","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2003-07-18","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"筑波大学"},{"subitem_text_value":"筑波大学"},{"subitem_text_value":"名古屋大学"},{"subitem_text_value":"豊橋技術科学大学"},{"subitem_text_value":"龍谷大学"},{"subitem_text_value":"徳島大学"},{"subitem_text_value":"信州大学"},{"subitem_text_value":"和歌山大学"},{"subitem_text_value":"ATR音声言語コミュニケーション研究所"},{"subitem_text_value":"ATR音声言語コミュニケーション研究所"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"University of Tsukuba","subitem_text_language":"en"},{"subitem_text_value":"University of Tsukuba","subitem_text_language":"en"},{"subitem_text_value":"Nagoya University","subitem_text_language":"en"},{"subitem_text_value":"Toyohashi University of Technology","subitem_text_language":"en"},{"subitem_text_value":"Ryukoku University","subitem_text_language":"en"},{"subitem_text_value":"University of Tokushima","subitem_text_language":"en"},{"subitem_text_value":"Shinshu University","subitem_text_language":"en"},{"subitem_text_value":"Wakayama University","subitem_text_language":"en"},{"subitem_text_value":"ATR Spoken Language Translation Research Labs.","subitem_text_language":"en"},{"subitem_text_value":"ATR Spoken Language Translation Research Labs.","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/57231/files/IPSJ-SLP03047018.pdf"},"date":[{"dateType":"Available","dateValue":"2005-07-18"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP03047018.pdf","filesize":[{"value":"381.5 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":"e00c3690-7340-4d4e-946d-fa0b359c76cb","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2003 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"山田, 武志"},{"creatorName":"岡田, 治郎"},{"creatorName":"武田, 一哉"},{"creatorName":"北岡, 教英"},{"creatorName":"藤本, 雅清"},{"creatorName":"黒岩, 眞吾"},{"creatorName":"山本, 一公"},{"creatorName":"西浦, 敬信"},{"creatorName":"水町, 光徳"},{"creatorName":"中村, 哲"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Takeshi, Yamada","creatorNameLang":"en"},{"creatorName":"Jiro, Okada","creatorNameLang":"en"},{"creatorName":"Kazuya, Takeda","creatorNameLang":"en"},{"creatorName":"Norihide, Kitaoka","creatorNameLang":"en"},{"creatorName":"Masakiyo, Fujimoto","creatorNameLang":"en"},{"creatorName":"Shingo, Kuroiwa","creatorNameLang":"en"},{"creatorName":"Kazumasa, Yamamoto","creatorNameLang":"en"},{"creatorName":"Takanobu, Nishiura","creatorNameLang":"en"},{"creatorName":"Mitsunori, Mizumachi","creatorNameLang":"en"},{"creatorName":"Satoshi, Nakamura","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":"様々な雑音条件下でロバストな音声認識を実現するためには，複数の雑音抑圧手法の統合が有効であると考えられる．本稿では，4つの雑音抑圧手法時間方向スムージングを用いたスペクトルサブトラクション法，時間領域SVDに基づく音声強調，GMMに基づく音声信号推定，ピッチ同期KLT）とそれらの組合せの有効性を，AURORA-2Jを用いて調べた．その結果，雑音条件によって最適な手法・組合せは異なっており，雑音条件に適したものを適宜選択することにより，認識性能を大幅に改善できることが明らかとなった．また，Multicondition trainingの場合は，雑音抑圧量を増やしても，必ずしも認識性能の改善につながらないことが分かった．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"To achieve high recognition performance for a wide variety of noise and for a wide range of signal-to-noise ratios, this paper presents the integration of four noise reduction algorithms: spectral subtraction with smoothing of time direction, temporal domain SVD-based speech enhancement, GMM-based speech estimation and KLT-based comb-filtering. Recognition results on the AURORA-2J task show that the effectiveness of these algorithms and their combinations strongly depends on noise conditions, and excessive noise reduction tends to degrade recognition performance in multicondition training.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"100","bibliographic_titles":[{"bibliographic_title":"情報処理学会研究報告音声言語情報処理（SLP）"}],"bibliographicPageStart":"95","bibliographicIssueDates":{"bibliographicIssueDate":"2003-07-18","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"75(2003-SLP-047)","bibliographicVolumeNumber":"2003"}]},"relation_version_is_last":true,"weko_creator_id":"1"},"id":57231,"updated":"2025-01-22T04:36:15.815817+00:00","links":{},"created":"2025-01-18T23:20:28.720172+00:00"}