{"created":"2025-01-18T23:20:36.087598+00:00","links":{},"updated":"2025-01-22T04:31:48.616836+00:00","id":57387,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00057387","sets":["1164:5159:5204:5205"]},"path":["5205"],"owner":"1","recid":"57387","title":["発話速度に依存したデコーディングと音響モデルの適応"],"pubdate":{"attribute_name":"公開日","attribute_value":"2001-12-20"},"_buckets":{"deposit":"5a3ee165-5b29-47a3-8483-8e6b8bd75615"},"_deposit":{"id":"57387","pid":{"type":"depid","value":"57387","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"発話速度に依存したデコーディングと音響モデルの適応","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"発話速度に依存したデコーディングと音響モデルの適応"},{"subitem_title":"Speaking - Rate Dependent Decoding and Adaptation for Spontaneous Lecture Speech Recognition","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2001-12-20","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"}]},"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"}]},"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/57387/files/IPSJ-SLP01039020.pdf"},"date":[{"dateType":"Available","dateValue":"2003-12-20"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP01039020.pdf","filesize":[{"value":"1.1 MB"}],"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":"430f6c82-3545-4646-8fa5-0d86d582b46f","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2001 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"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":"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":"大語彙の話し言葉音声認識における発話速度に関する問題に焦点をあてた認識手法について報告する。話し言葉音声では発話速度は一般に速く変動も大きい為、認識が困難である。実際に認識結果において、特に速い音声で認識率が低い事、および発話速度の速い音声と遅い音声では認識誤り傾向に明確なさがあることを確認した。そこで、発話速度に応じて最適な音響分析フレーム・音素モデル・デコーディングパラメータを選択的に適用し認識を行う手法を提案する。発話速度の自動推定を組み合わせる事により認識率の向上を得た。さらに、発話速度情報を話者適応に用いる手法についても検討を行う。速い発話と遅い発話のそれぞれを指向した異なる話者適応モデルを構築しそれらを選択的に適用することで、速度情報を用いない適応よりも効率的な適応が行えることを認識した。","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"This paper addresses the problem of speaking rate in large vocabulary spontaneous speech recognition. In spontaneous lecture speech, the speaking rate is generally fast and may vary a lot within a talk. We also observed different error tendencies for fast and slow speech segments. Therefore, we first present a speaking-rate dependent decoding strategy that applies the most adequate acoustic analysis, phone models and decoding parameters according to the speaking rate. Several methods are investigared and their selective application leads to accuracy improvement. We also propose to make use of speaking-rate information in speaker adaptation, in which the different adapted models are set up for fast and slow utterances. It is confirmed that the method is more effective than normal adaptation.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"122","bibliographic_titles":[{"bibliographic_title":"情報処理学会研究報告音声言語情報処理（SLP）"}],"bibliographicPageStart":"117","bibliographicIssueDates":{"bibliographicIssueDate":"2001-12-20","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"123(2001-SLP-039)","bibliographicVolumeNumber":"2001"}]},"relation_version_is_last":true,"weko_creator_id":"1"}}