{"created":"2021-03-01T06:15:29.859673+00:00","id":8768,"links":{},"metadata":{"_buckets":{"deposit":"ddedd39a-e176-4d39-8909-25641f62550d"},"_deposit":{"id":"8768","owners":[],"pid":{"revision_id":0,"type":"depid","value":"8768"},"status":"published"},"_oai":{"id":"oai:nagoya.repo.nii.ac.jp:00008768","sets":["312:313:314"]},"author_link":["24678","24679","24680","24681","24682","24683","24684","24685"],"item_10_alternative_title_19":{"attribute_name":"その他のタイトル","attribute_value_mlt":[{"subitem_alternative_title":"Speech Starter: Speech Input Interface Capable of Endpoint Detection by Using Filled Pauses","subitem_alternative_title_language":"en"}]},"item_10_biblio_info_6":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"2007","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"5","bibliographicPageEnd":"2011","bibliographicPageStart":"2001","bibliographicVolumeNumber":"48","bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌","bibliographic_titleLang":"ja"}]}]},"item_10_description_4":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"本論文では,ユーザが有声休止(母音の引き延ばし)によって言い淀んだ後に音声入力することで,雑音環境下での発話区間検出を容易にする｢音声スタータ｣という音声インタフェース機能を提案する.通常の音声認識システムでは,入力音響信号から発話区間を検出した後に,その区間に対して音声認識結果を得る.しかし非定常な雑音環境下では,頑健に発話区間を検出することが困難なため,音声認識誤りを生じることが多かった.音声スタータでは,ユーザが｢えー｣や｢あのー｣のように有声休止を発話の先頭(発話区間の始端)で故意に発声することで,システムに音声認識してほしい発話を明示的に指定することを可能にする.有声休止はパワーの大きい母音が持続することから,雑音環境下でも頑健に検出でき,発話区間検出の精度を向上させることができる.さらに,音声スタータではマイク以外のデバイスが不要でハンズフリーな音声認織を実現でき,日常会話でも言い淀んでから話し始めることがよくあるためにユーザの負担も少ないという利点がある.実際に7種類の雑音環境下で音声認識実験をしたところ,特にSNR10dBにおいて従来の他の発話区間検出手法を用いた場合よりも,音声スタータを用いた場合の方が検出性能が高かった. ","subitem_description_language":"ja","subitem_description_type":"Abstract"},{"subitem_description":"This paper describes a speech interface function, called Speech Starter, which enables noise-robust endpoint (utterance) detection by having a user utter a filled pause (a vowellengthening hesitation) at the beginning of each utterance. Most current speech recognizers first detect a utterance with its endpoints and then recognize the detected utterance. When speech recognizers are used in a noisy environment, a typical recognition error is caused by incorrect endpoints because their automatic detection is likely to be disturbed by non-stationary noise. Speech Starter enables a user to specify the beginning of each utterance with an intentional filled pause (e.g., \"er...\"), which is used as a trigger to start speech-recognition processes. Because a filled pause contains a lengthened vowel with high power and can be detected robustly in a noisy environment, practical robust endpoint detection is achieved.","subitem_description_language":"en","subitem_description_type":"Abstract"}]},"item_10_identifier_60":{"attribute_name":"URI","attribute_value_mlt":[{"subitem_identifier_type":"HDL","subitem_identifier_uri":"http://hdl.handle.net/2237/10519"}]},"item_10_publisher_32":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"item_10_rights_12":{"attribute_name":"権利","attribute_value_mlt":[{"subitem_rights":"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. All Rights Reserved, Copyright (C) Information Processing Society of Japan. Comments are welcome. Mail to address: 　editj<at>ipsj.or.jp, please.","subitem_rights_language":"en"}]},"item_10_select_15":{"attribute_name":"著者版フラグ","attribute_value_mlt":[{"subitem_select_item":"publisher"}]},"item_10_source_id_7":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"03875806","subitem_source_identifier_type":"PISSN"}]},"item_10_text_14":{"attribute_name":"フォーマット","attribute_value_mlt":[{"subitem_text_value":"application/pdf"}]},"item_1615787544753":{"attribute_name":"出版タイプ","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":"後藤, 真孝","creatorNameLang":"ja"}],"nameIdentifiers":[{"nameIdentifier":"24678","nameIdentifierScheme":"WEKO"}]},{"creatorNames":[{"creatorName":"Goto, Masataka","creatorNameLang":"en"}],"nameIdentifiers":[{"nameIdentifier":"24679","nameIdentifierScheme":"WEKO"}]},{"creatorNames":[{"creatorName":"北山, 広治","creatorNameLang":"ja"}],"nameIdentifiers":[{"nameIdentifier":"24680","nameIdentifierScheme":"WEKO"}]},{"creatorNames":[{"creatorName":"Kitayama, Koji","creatorNameLang":"en"}],"nameIdentifiers":[{"nameIdentifier":"24681","nameIdentifierScheme":"WEKO"}]},{"creatorNames":[{"creatorName":"伊藤, 克亘","creatorNameLang":"ja"}],"nameIdentifiers":[{"nameIdentifier":"24682","nameIdentifierScheme":"WEKO"}]},{"creatorNames":[{"creatorName":"Ito, katunobu","creatorNameLang":"en"}],"nameIdentifiers":[{"nameIdentifier":"24683","nameIdentifierScheme":"WEKO"}]},{"creatorNames":[{"creatorName":"小林, 哲則","creatorNameLang":"ja"}],"nameIdentifiers":[{"nameIdentifier":"24684","nameIdentifierScheme":"WEKO"}]},{"creatorNames":[{"creatorName":"Kobayashi, Tetsunori","creatorNameLang":"en"}],"nameIdentifiers":[{"nameIdentifier":"24685","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":"2018-02-19"}],"displaytype":"detail","filename":"48-5-2001.pdf","filesize":[{"value":"1.1 MB"}],"format":"application/pdf","licensetype":"license_note","mimetype":"application/pdf","url":{"label":"48-5-2001.pdf","objectType":"fulltext","url":"https://nagoya.repo.nii.ac.jp/record/8768/files/48-5-2001.pdf"},"version_id":"41cb7299-d162-445c-a913-8227650c2b1f"}]},"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":"音声スタータ:有声休止による発話開始の指定が可能な音声入力インタフェース","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"音声スタータ:有声休止による発話開始の指定が可能な音声入力インタフェース","subitem_title_language":"ja"}]},"item_type_id":"10","owner":"1","path":["314"],"pubdate":{"attribute_name":"PubDate","attribute_value":"2008-09-12"},"publish_date":"2008-09-12","publish_status":"0","recid":"8768","relation_version_is_last":true,"title":["音声スタータ:有声休止による発話開始の指定が可能な音声入力インタフェース"],"weko_creator_id":"1","weko_shared_id":-1},"updated":"2023-01-16T04:49:02.906908+00:00"}