{"links":{},"id":56979,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00056979","sets":["1164:5159:5180:5183"]},"path":["5183"],"owner":"1","recid":"56979","title":["ドメイン内の信頼度と談話の整合性を用いた音声認識誤りの検出"],"pubdate":{"attribute_name":"公開日","attribute_value":"2005-07-15"},"_buckets":{"deposit":"74169a09-f1eb-4f6e-950d-7c36e9666bdf"},"_deposit":{"id":"56979","pid":{"type":"depid","value":"56979","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"ドメイン内の信頼度と談話の整合性を用いた音声認識誤りの検出","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"ドメイン内の信頼度と談話の整合性を用いた音声認識誤りの検出"},{"subitem_title":"Incorporating In-domain Confidence and Discourse Coherence Measures in Utterance Verification","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2005-07-15","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 知能情報学専攻/ATR 音声言語コミュニケーション研究所"},{"subitem_text_value":"京都大学 情報学研究科 知能情報学専攻/ATR 音声言語コミュニケーション研究所"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Informatics, Kyoto University/ATR Spoken Language Translation Laboratories","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Informatics, Kyoto University/ATR Spoken Language Translation Laboratories","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"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/56979/files/IPSJ-SLP05057007.pdf"},"date":[{"dateType":"Available","dateValue":"2007-07-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP05057007.pdf","filesize":[{"value":"161.0 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":"6ed81442-5b6c-4382-aacf-13abf79fed4c","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2005 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"レーン, イアン"},{"creatorName":"河原, 達也"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Ian, R.Lane","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":"音声認識結果の信頼度尺度に関する従来研究は、一般に音声認識デコーダから直接得られる単語尤度などの`低次の'情報に基づいている。それに対して、`高次の'知識に基づいた信頼度尺度を用いる発話検証手法を提案する。本稿では、ドメイン内の信頼度尺度（発話がシステムの扱うドメイン内である信頼度）と、談話の整合性に関する信頼度尺度（対話における発話の関連性・一貫性に関する尺度）を提案する。これらの2つの提案手法を、従来より広く用いられている一般化事後確率（GPP: generalized posterior probability）と組み合わせることによって、総合的な信頼度尺度を求める。ATR の音声翻訳システムを介した自然対話音声を用いて評価実験を行った結果、実際に認識誤り検出性能の改善が得られた。","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Conventional confidence measures for assessing the reliability of ASR output are typically derived from `low-level' information which is obtained during speech recognition decoding. In contrast to these approaches, we propose a novel utterance verification scheme which incorporates confidence measures derived from `high-level' knowledge sources. Specifically, we investigate two measures: in-domain confidence, the degree of match between the input utterance and the application domain of the back-end system, and discourse coherence, the consistency between consecutive utterances in a dialogue session. A joint verification confidence is generated by combining these two measures with an orthodox measure based on GPP (generalized posterior probability). The proposed verification scheme was evaluated on spontaneous dialogue via the ATR speech-to-speech translation system. The two proposed measures were effective in improving verification accuracy. ","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"42","bibliographic_titles":[{"bibliographic_title":"情報処理学会研究報告音声言語情報処理（SLP）"}],"bibliographicPageStart":"37","bibliographicIssueDates":{"bibliographicIssueDate":"2005-07-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"69(2005-SLP-057)","bibliographicVolumeNumber":"2005"}]},"relation_version_is_last":true,"weko_creator_id":"1"},"created":"2025-01-18T23:20:16.710875+00:00","updated":"2025-01-22T04:42:51.772441+00:00"}