{"created":"2025-01-18T23:20:45.020729+00:00","updated":"2025-01-22T04:26:58.383365+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00057577","sets":["1164:5159:5216:5217"]},"path":["5217"],"owner":"1","recid":"57577","title":["ニュース音声認識のための（n≧4）- gramを併用する言語モデル"],"pubdate":{"attribute_name":"公開日","attribute_value":"1999-12-20"},"_buckets":{"deposit":"a6c6dca8-810b-4db6-9929-9d5a924e064c"},"_deposit":{"id":"57577","pid":{"type":"depid","value":"57577","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"ニュース音声認識のための（n≧4）- gramを併用する言語モデル","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"ニュース音声認識のための（n≧4）- gramを併用する言語モデル"},{"subitem_title":"A New Language Model by using (n≧4) - gram for Broadcast News Speech Transcription","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"1999-12-20","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"NHK放送技術研究所"},{"subitem_text_value":"ATR音声翻訳通信研究所"},{"subitem_text_value":"NHK放送技術研究所"},{"subitem_text_value":"NHK放送技術研究所"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"NHK Science and Technical Research Laboratories","subitem_text_language":"en"},{"subitem_text_value":"ATR Interpreting Telecommunications Research Laboratories","subitem_text_language":"en"},{"subitem_text_value":"NHK Science and Technical Research Laboratories","subitem_text_language":"en"},{"subitem_text_value":"NHK Science and Technical Research Laboratories","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/57577/files/IPSJ-SLP99029032.pdf"},"date":[{"dateType":"Available","dateValue":"2001-12-20"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP99029032.pdf","filesize":[{"value":"513.2 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":"f6e616f1-f021-4c3f-ba06-8b04235f4cb2","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 1999 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"加藤, 直人"},{"creatorName":"浦谷則好"},{"creatorName":"江原暉将"},{"creatorName":"安藤, 彰男"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Naoto, Katoh","creatorNameLang":"en"},{"creatorName":"Noriyoshi, Uratani","creatorNameLang":"en"},{"creatorName":"Terumasa, Ehara","creatorNameLang":"en"},{"creatorName":"Akio, Ando","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":"音声認識の精度向上には言語制約が強い言語モデルを構成すること必要であり，その一つの方法がタスク適応である．一方で，タスク適応しすぎると頑健性が損なわれるという問題がある．本稿では(n≧4)?gramを利用することによりタスクへの適応をしつつ，2 3-gramも利用することで頑健性もそれほど損なわない言語モデルについて述べる．提案する言語モデルでは(n≧4)-gramを，従来のn-gramのように宣言的知識として記憶するのではなく，単語出現位置辞書という概念を導入して手続き的知識として記憶することによりそれほどデータ量を増やすことなく利用している．本言語モデルを放送ニュースに応用し，そのperplexityによる評価実験を行ったところ，良好な結果を得た．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Language model adaptation is one of the important methods to construct a speech recognition system for practical use. The conventional adaptation methods adjusted n-gram estimated from various task corpora to ones from a specific task corpus. However the methods are not so effective in some tasks such as TV news, because some of TV news does not use news scripts. This paper proposes a new language model for Broadcast news speech transcription. Our model can not only adapt to a specific task but also deal with the more tasks by dynamically using (n≧4)-gram and 2,3-gram. The proposed method can reduce amount of (n≧4)-gram data by registering it as procedural knowledge through WPD (Word Position Data). The WPD represents each position of words in a task corpus and is automatically composed of the corpus. We conducted a serirs of experiments to evaluate our model and obtained a good result.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"192","bibliographic_titles":[{"bibliographic_title":"情報処理学会研究報告音声言語情報処理（SLP）"}],"bibliographicPageStart":"187","bibliographicIssueDates":{"bibliographicIssueDate":"1999-12-20","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"108(1999-SLP-029)","bibliographicVolumeNumber":"1999"}]},"relation_version_is_last":true,"weko_creator_id":"1"},"id":57577,"links":{}}