{"created":"2023-07-25T10:25:30.213083+00:00","id":3865,"links":{},"metadata":{"_buckets":{"deposit":"de48da48-29da-4605-ba5e-9696fbb0cf6e"},"_deposit":{"created_by":4,"id":"3865","owners":[4],"pid":{"revision_id":0,"type":"depid","value":"3865"},"status":"published"},"_oai":{"id":"oai:naist.repo.nii.ac.jp:00003865","sets":["34:35"]},"author_link":["6494","331","6495","6496"],"item_7_alternative_title_1":{"attribute_name":"その他のタイトル","attribute_value_mlt":[{"subitem_alternative_title":"Many-to-many Alignment Algorithm for Automatic Pronunciation Annotation on Japanese Unknown Words","subitem_alternative_title_language":"en"}]},"item_7_biblio_info_9":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"2013-02-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"2","bibliographicPageEnd":"462","bibliographicPageStart":"452","bibliographicVolumeNumber":"54"}]},"item_7_description_7":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"音声ドキュメント検索や音声検索のような固有名詞や新語を扱うアプリケーションの発達とともに,未知語に対する頑健な自動発音付与の必要性は増加している.未知語への自動発音付与手法として統計的アプローチやWebテキストマイニングによるアプローチがある.これらには単語の表記と発音を単語(形態素)よりも小さい単位で対応付けたデータが不可欠である.本論文では日本語の未知語に対する発音付与の性能向上を目的として,表記と発音の対応付けの精度を劣化させずに,未知語を表現する能力が高い小さい単位での対応付けを求めるアライメントアルゴリズムを提案する.また,Webテキストマイニングを用いた日本語の未知語に対する自動発音付与により提案手法の評価を行った.評価実験の結果,提案手法は従来手法が持つ精度をほとんど劣化させずに,未知語に対する汎化能力を表す再現率を約3.9ポイント改善した.","subitem_description_language":"ja","subitem_description_type":"Abstract"},{"subitem_description":"The need for robust pronunciation annotation on unknown words has been increasing with the development of an application that deals with proper nouns and brand-new words, such as Spoken Document Retrieval and Voice Search. In robust pronunciation annotation on unknown words, the alignment between graphemes and phonemes is vital data. In this paper, for the purpose of the improving pronunciation annotation on Japanese unknown words, we propose the alignment algorithm that requires a mapping with small unit having high expression ability on unknown words while avoiding degradation of the accuracy of a mapping between graphemes and phonemes. An evaluation experiment of a many-to-many alignment by automatic pronunciation annotation using Web text mining is also performed. That experimental result shows that the proposed many-to-many alignment obtains 3.9 point improvement on recall rate that represents the generalization ability for unknown words while avoiding degradation of the accuracy of the pronunciation annotation compared with the conventional approach.","subitem_description_language":"en","subitem_description_type":"Abstract"}]},"item_7_rights_11":{"attribute_name":"出版者URL","attribute_value_mlt":[{"subitem_rights":"http://id.nii.ac.jp/1001/00090249"}]},"item_7_rights_18":{"attribute_name":"権利","attribute_value_mlt":[{"subitem_rights":"Copyright (C) 2013 情報処理学会 ここに掲載した著作物の利用に関する注意: 本著作物の著作権は（社）情報処理学会に帰属します。本著作物は著作権者である情報処理学会の許可のもとに掲載するものです。ご利用に当たっては「著作権法」ならびに「情報処理学会倫理綱領」に従うことをお願いいたします。","subitem_rights_language":"ja"},{"subitem_rights":"Notice for the use of this material: The copyright of this material is retained by the Information Processing Society of Japan (IPSJ). This material is published on this web site with the agreement of the author(s) and the IPSJ. Please be complied with Copyright Law of Japan and the Code of Ethics of the IPSJ if any users wish to reproduce, make derivative work, distribute or make available to the public any part or whole thereof.","subitem_rights_language":"en"}]},"item_7_source_id_12":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"0387-5806","subitem_source_identifier_type":"ISSN"}]},"item_7_source_id_14":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00116647","subitem_source_identifier_type":"NCID"}]},"item_7_version_type_20":{"attribute_name":"著者版フラグ","attribute_value_mlt":[{"subitem_version_resource":"http://purl.org/coar/version/c_970fb48d4fbd8a85","subitem_version_type":"VoR"}]},"item_access_right":{"attribute_name":"アクセス権","attribute_value_mlt":[{"subitem_access_right":"open access","subitem_access_right_uri":"http://purl.org/coar/access_right/c_abf2"}]},"item_creator":{"attribute_name":"著者","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"久保, 慶伍","creatorNameLang":"ja"}],"nameIdentifiers":[{"nameIdentifier":"6494","nameIdentifierScheme":"WEKO"}]},{"creatorNames":[{"creatorName":"川波, 弘道","creatorNameLang":"ja"}],"nameIdentifiers":[{"nameIdentifier":"331","nameIdentifierScheme":"WEKO"},{"nameIdentifier":"80335489","nameIdentifierScheme":"e-Rad","nameIdentifierURI":"https://kaken.nii.ac.jp/ja/search/?qm=80335489"}]},{"creatorNames":[{"creatorName":"猿渡, 洋","creatorNameLang":"ja"}],"nameIdentifiers":[{"nameIdentifier":"6495","nameIdentifierScheme":"WEKO"}]},{"creatorNames":[{"creatorName":"鹿野, 清宏","creatorNameLang":"ja"}],"nameIdentifiers":[{"nameIdentifier":"6496","nameIdentifierScheme":"WEKO"}]}]},"item_files":{"attribute_name":"ファイル情報","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_date","date":[{"dateType":"Available","dateValue":"2023-03-02"}],"displaytype":"detail","filename":"JInfoProc_54_2_452.pdf","filesize":[{"value":"1.7 MB"}],"format":"application/pdf","licensetype":"license_note","mimetype":"application/pdf","url":{"label":"fulltext","objectType":"fulltext","url":"https://naist.repo.nii.ac.jp/record/3865/files/JInfoProc_54_2_452.pdf"},"version_id":"67637750-6d95-43ef-967b-38950ed3dca9"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"文字列アライメント","subitem_subject_language":"ja","subitem_subject_scheme":"Other"},{"subitem_subject":"未知語","subitem_subject_language":"ja","subitem_subject_scheme":"Other"},{"subitem_subject":"自動発音付与","subitem_subject_language":"ja","subitem_subject_scheme":"Other"},{"subitem_subject":"Webテキストマイニング","subitem_subject_language":"ja","subitem_subject_scheme":"Other"},{"subitem_subject":"Joint multigram","subitem_subject_language":"en","subitem_subject_scheme":"Other"},{"subitem_subject":"character alignment","subitem_subject_language":"en","subitem_subject_scheme":"Other"},{"subitem_subject":"out-of-vocabulary","subitem_subject_language":"en","subitem_subject_scheme":"Other"},{"subitem_subject":"pronunciation annotation","subitem_subject_language":"en","subitem_subject_scheme":"Other"},{"subitem_subject":"Web text mining","subitem_subject_language":"en","subitem_subject_scheme":"Other"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourcetype":"journal article","resourceuri":"http://purl.org/coar/resource_type/c_6501"}]},"item_title":"日本語の未知語に対する発音付与のための多対多アライメント","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"日本語の未知語に対する発音付与のための多対多アライメント","subitem_title_language":"ja"}]},"item_type_id":"7","owner":"4","path":["35"],"pubdate":{"attribute_name":"PubDate","attribute_value":"2013-11-19"},"publish_date":"2013-11-19","publish_status":"0","recid":"3865","relation_version_is_last":true,"title":["日本語の未知語に対する発音付与のための多対多アライメント"],"weko_creator_id":"4","weko_shared_id":-1},"updated":"2023-11-14T10:52:17.537811+00:00"}