{"links":{},"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00067053","sets":["1164:5159:5160:5936"]},"path":["5936"],"owner":"10","recid":"67053","title":["文脈を考慮した確率的モデルによる話し言葉の整形"],"pubdate":{"attribute_name":"公開日","attribute_value":"2009-12-14"},"_buckets":{"deposit":"56f33f14-1968-4321-ad34-322399153c33"},"_deposit":{"id":"67053","pid":{"type":"depid","value":"67053","revision_id":0},"owners":[10],"status":"published","created_by":10},"item_title":"文脈を考慮した確率的モデルによる話し言葉の整形","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"文脈を考慮した確率的モデルによる話し言葉の整形"},{"subitem_title":"Context-sensitive Statistical Models for Speaking-style Transformation","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"【Session-9 音声検索・要約】","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2009-12-14","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"},{"subitem_text_value":"京都大学情報学研究科"},{"subitem_text_value":"京都大学情報学研究科"},{"subitem_text_value":"京都大学情報学研究科"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Informatics, Kyoto University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Informatics, Kyoto University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Informatics, Kyoto University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Informatics, Kyoto University","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/67053/files/IPSJ-SLP09079017.pdf"},"date":[{"dateType":"Available","dateValue":"2011-12-14"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP09079017.pdf","filesize":[{"value":"315.8 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":"9044d0c9-2e96-47e8-bc79-01949ccaf3ca","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2009 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Graham, Neubig"},{"creatorName":"秋田, 祐哉"},{"creatorName":"森, 信介"},{"creatorName":"河原, 達也"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Graham, Neubig","creatorNameLang":"en"},{"creatorName":"Yuya, Akita","creatorNameLang":"en"},{"creatorName":"Shinsuke, Mori","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":"自動音声認識 （ASR） の結果には認識誤りのみならず，言いよどみや口語的表現など，会議録にふさわしくない現象が多く含まれている．これらの現象を整形し，自然な会議録を作成するために，認識結果 （または忠実な書き起こし） と会議録を異なる言語とみなし，統計的機械翻訳を用いて認識結果から会議録へと “翻訳” する．本研究では，この枠組みの中で 2 つの手法を提案する．まず，文脈情報を考慮した翻訳モデルを導入し，システムのさらなる精度向上を目指す．また，翻訳モデルの条件付き確率と同時確率の対数線形補間を行うことで，高頻度の翻訳パターンを優先的に利用することを可能とする．有限状態トランスデューサー （WFST） による実装を行い，国会会議録と音声認識結果を用いた評価実験を行った．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Automatic speech recognition (ASR) results contain not only recognition errors, but also disfluencies and colloquial expressions that are not appropriate for inclusion in official transcripts. In order to correct these phenomena and create natural transcripts, we treat ASR results (or faithful transcripts) and official transcripts as different languages and use techniques from statistical machine translation (SMT) to “translate” between the two. In this paper, we present two novel methods in this framework. First, we introduce a technique to create context-sensitive translation models, improving the modeling accuracy. Second, we use log-linear interpolation to combine the translation model’s joint and conditional probabilities, allowing for frequently observed patterns to be given higher priority. A system containing these improvements was implemented using weighted finite state transducers, and an evaluation was performed on transcripts from meetings of the Japanese Diet (national congress).","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"音声言語情報処理（SLP）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2009-12-14","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"17","bibliographicVolumeNumber":"2009-SLP-79"}]},"relation_version_is_last":true,"weko_creator_id":"10"},"updated":"2025-01-22T00:44:46.700171+00:00","created":"2025-01-18T23:27:39.088238+00:00","id":67053}