{"created":"2025-01-18T23:20:01.245482+00:00","links":{},"updated":"2025-01-22T04:52:51.579739+00:00","id":56648,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00056648","sets":["1164:5159:5162:5165"]},"path":["5165"],"owner":"1","recid":"56648","title":["同時通訳者の知識と韻律情報を用いた講演文章のチャンキング"],"pubdate":{"attribute_name":"公開日","attribute_value":"2008-07-11"},"_buckets":{"deposit":"bff3337e-1495-4b14-9eac-0649937de45b"},"_deposit":{"id":"56648","pid":{"type":"depid","value":"56648","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"同時通訳者の知識と韻律情報を用いた講演文章のチャンキング","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"同時通訳者の知識と韻律情報を用いた講演文章のチャンキング"},{"subitem_title":"Segmentation of spoken monologue using human interpreter's knowledge and prosodic features","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2008-07-11","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"独立行政法人情報通信研究機構知識創成コミュニケーション研究センター/ATR 音声言語コミュニケーション研究所/京都大学情報学研究科"},{"subitem_text_value":"独立行政法人情報通信研究機構知識創成コミュニケーション研究センター/ATR 音声言語コミュニケーション研究所"},{"subitem_text_value":" 独立行政法人情報通信研究機構知識創成コミュニケーション研究センター/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":"Knowledge Creating Communication Research Center, National Institute of Information and Communication Technology / ATR Spoken Language Communication Research Labs. / School of Informatics, Kyoto University","subitem_text_language":"en"},{"subitem_text_value":"Knowledge Creating Communication Research Center, National Institute of Information and Communication Technology / ATR Spoken Language Communication Research Labs.","subitem_text_language":"en"},{"subitem_text_value":"Knowledge Creating Communication Research Center, National Institute of Information and Communication Technology / 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/56648/files/IPSJ-SLP08072015.pdf"},"date":[{"dateType":"Available","dateValue":"2010-07-11"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP08072015.pdf","filesize":[{"value":"1.3 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":"5b023b96-fe93-4151-b3ec-bd0a208758bb","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2008 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"清水, 徹"},{"creatorName":"中村, 哲"},{"creatorName":"河原, 達也"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Tohru, Shimizu","creatorNameLang":"en"},{"creatorName":"Satoshi, Nakamura","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":"文の区切りが明確でない、一文が長くなる、文の途中に間 (ポーズ) が空くなどの現象が見られる自然な話し言葉を、適切な単位に区分化する処理が求められている。本稿では、区分化の単位として従来用いられている文や節に代わる、プロの同時通訳者が原言語からターゲット言語に変換する自然なタイミングである音声翻訳単位を提案し、同単位の特徴と、言語情報ならびに韻律情報を用いた音声翻訳単位境界の推定手法について述べる。ポーズを伴う音声翻訳単位境界では人間の境界付与精度に近い推定精度が得られ、ポーズを伴わない音声翻訳単位境界の推定精度は低いものの、韻律情報に基づく素性の導入により、推定精度の向上効果が確認された。","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"As automatic speech recognition and translation of long and complicated utterance cause more errors, there is increasing requirement for utterance segmentation techniques. This paper proposes speech translation unit (STU), which is a segment of an utterance which the human interpreter treats as a single cognitive unit, and also proposes speech translation unit boundary detection method by combining lexical features and prosodic features. An experimental evaluation using monologues shows that the introduction of the prosodic feature increases STU boundary detection accuracy by 7% for STU boundaries in the pause unit. ","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"86","bibliographic_titles":[{"bibliographic_title":"情報処理学会研究報告音声言語情報処理(SLP)"}],"bibliographicPageStart":"81","bibliographicIssueDates":{"bibliographicIssueDate":"2008-07-11","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"68(2008-SLP-072)","bibliographicVolumeNumber":"2008"}]},"relation_version_is_last":true,"weko_creator_id":"1"}}