{"links":{},"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00057472","sets":["1164:5159:5210:5211"]},"path":["5211"],"owner":"1","recid":"57472","title":["講演音声認識のための音響・言語モデルの検討"],"pubdate":{"attribute_name":"公開日","attribute_value":"2000-12-21"},"_buckets":{"deposit":"5a120d21-92cb-42bd-a1ee-91b939d66c98"},"_deposit":{"id":"57472","pid":{"type":"depid","value":"57472","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"講演音声認識のための音響・言語モデルの検討","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"講演音声認識のための音響・言語モデルの検討"},{"subitem_title":"Acoustic and Language Models for Lecture Speech Recognition","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2000-12-21","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"京都大学大学院情報学研究科知能情報学専攻"},{"subitem_text_value":"京都大学大学院情報学研究科知能情報学専攻"},{"subitem_text_value":"京都大学大学院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":"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/57472/files/IPSJ-SLP00034023.pdf"},"date":[{"dateType":"Available","dateValue":"2002-12-21"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP00034023.pdf","filesize":[{"value":"675.2 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":"011b2938-a79b-4e22-b9b1-32be8e73a68b","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2000 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, 一臣"},{"creatorName":"南條浩輝"},{"creatorName":"河原, 達也"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Kazuomi, Kato","creatorNameLang":"en"},{"creatorName":"Hiroaki, Nanjo","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":"融合研究プロジェクトにおいて構築が進められている講演音声と書き起こしテキストのデータベースを用いて、講演音声の認識のための音響・言語モデルを作成した。男性4名による音声・言語関係の学会講演を対象として評価を行った。これらのデータには話し言葉に固有の表現や発声の怠けなどが頻出する。利用できる講演の種類と量が多様であるため、音響・言語モデルそれぞれの学習にどのようなデータの組み合わせが適当であるかの検討を行った。音響モデルの学習には、学会講演というスタイルに一致させることの効果を確認し、言語モデルにおいても同様の傾向を確認した。現時点では平均59.8％の単語認識精度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":"The acoustic and language models for automatic lecture speech recognition are addressed. We have constructed both acoustic and language models with the lecture corpus that is being developed under the priority research program of the science and technology agency. In order to investigate the best data-set combination, we evaluated sets of models with conference lectures by four male experienced speakers. We confirmed significance of matching the training data-set style of the acoustic model to the conference lecture style. A similar tendency was also found in the language model training. So far, we have got a word accuracy of 59.8%.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"136","bibliographic_titles":[{"bibliographic_title":"情報処理学会研究報告音声言語情報処理（SLP）"}],"bibliographicPageStart":"131","bibliographicIssueDates":{"bibliographicIssueDate":"2000-12-21","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"119(2000-SLP-034)","bibliographicVolumeNumber":"2000"}]},"relation_version_is_last":true,"weko_creator_id":"1"},"updated":"2025-01-22T04:29:18.580756+00:00","created":"2025-01-18T23:20:40.109926+00:00","id":57472}