{"links":{},"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00056764","sets":["1164:5159:5168:5172"]},"path":["5172"],"owner":"1","recid":"56764","title":["言語モデルと発音辞書の統計的話し言葉変換に基づく国会音声認識"],"pubdate":{"attribute_name":"公開日","attribute_value":"2007-12-20"},"_buckets":{"deposit":"cc5cf580-fd40-4eed-83ab-24861fc16d19"},"_deposit":{"id":"56764","pid":{"type":"depid","value":"56764","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"言語モデルと発音辞書の統計的話し言葉変換に基づく国会音声認識","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"言語モデルと発音辞書の統計的話し言葉変換に基づく国会音声認識"},{"subitem_title":"Automatic Speech Recognition of Congressional Speech Based on Statistical Style Transformation of Language Model and Pronunciation Model","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2007-12-20","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"京都大学学術情報メディアセンター"},{"subitem_text_value":"京都大学学術情報メディアセンター"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Academic Center for Computing and Media Studies, Kyoto University","subitem_text_language":"en"},{"subitem_text_value":"Academic Center for Computing and Media Studies, 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/56764/files/IPSJ-SLP07069011.pdf"},"date":[{"dateType":"Available","dateValue":"2009-12-20"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP07069011.pdf","filesize":[{"value":"537.9 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":"9f06dce2-b2d0-4750-9d47-ddef5f2d63de","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2007 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"秋田, 祐哉"},{"creatorName":"河原, 達也"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Yuya, AKITA","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":"我々は，国会などの話し言葉音声認識のために，言語モデルと発音辞書を話し言葉スタイルに変換する手法を提案している．提案法では，発話の忠実な書き起こしとこれに対応する正書体のデータの相違点が統計的に抽出され，これをもとに確率的な変換パターンからなる変換モデルが言語モデルと発音辞書のそれぞれに対して構成される．このモデルに基づき，言語モデルに対しては話し言葉の N-gram の予測と統計頻度の推定を行う．一方発音辞書に対しては，話し言葉特有の発音変動の予測および発音確率の推定を行う．生成された話し言葉スタイルの言語モデルと発音辞書を衆議院の委員会会議音声において評価したところ，従来のモデルと比較して単語誤り率が絶対値でそれぞれ 0.6％～0.7％・1.0％改善し，これらの併用により合計で 1.7％の削減を得ることができた．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"For automatic speech recognition (ASR) of spontaneous speech such as congressional meetings, we have been proposing statistical transformation methods of language model and pronunciation model. In these methods, differences between faithful transcripts and orthographical transcripts are statistically extracted. Then, transformation models which consist of probabilistic transformation patterns are derived from the statistics for language model and pronunciation model. For language model, the transformation model predicts spoken-style N-gram entries with estimated occurrence counts. For pronunciation model, pronunciation variants and their probabilities are predicted by the transformation model. The language model and pronunciation model generated by the proposed methods were evaluated on ASR of committee meetings of Japanese National Congress (Diet), and realized absolute reduction of word error rates by 0.6-0.7％ and 1.0％, respectively, compared with models produced by conventional methods. Finally, total reduction of 1.7％ was obtained by combining both models.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"66","bibliographic_titles":[{"bibliographic_title":"情報処理学会研究報告音声言語情報処理（SLP）"}],"bibliographicPageStart":"61","bibliographicIssueDates":{"bibliographicIssueDate":"2007-12-20","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"129(2007-SLP-069)","bibliographicVolumeNumber":"2007"}]},"relation_version_is_last":true,"weko_creator_id":"1"},"updated":"2025-01-22T04:48:32.371834+00:00","created":"2025-01-18T23:20:06.617713+00:00","id":56764}