{"created":"2024-11-22T07:44:47.107416+00:00","id":2008800,"links":{},"metadata":{"_buckets":{"deposit":"748c169e-1178-40bd-81dc-2834d50cc97b"},"_deposit":{"created_by":7,"id":"2008800","owners":[7],"pid":{"revision_id":0,"type":"depid","value":"2008800"},"status":"published"},"_oai":{"id":"oai:tokushima-u.repo.nii.ac.jp:02008800","sets":["1713853213384:1713853295607"]},"author_link":["728","942"],"control_number":"2008800","item_10001_alternative_title_1":{"attribute_name":"タイトル別表記","attribute_value_mlt":[{"subitem_alternative_title":"E2E SPEECH RECOGNITION WITH CTC AND LOCAL ATTENTION","subitem_alternative_title_language":"en"}]},"item_10001_biblio_info_7":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"2020-11-23","bibliographicIssueDateType":"Issued"},"bibliographicPageStart":"e25","bibliographicVolumeNumber":"9","bibliographic_titles":[{"bibliographic_title":"APSIPA Transactions on Signal and Information Processing","bibliographic_titleLang":"en"}]}]},"item_10001_description_5":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"Many end-to-end, large vocabulary, continuous speech recognition systems are now able to achieve better speech recognition performance than conventional systems. Most of these approaches are based on bidirectional networks and sequence-to-sequence modeling however, so automatic speech recognition (ASR) systems using such techniques need to wait for an entire segment of voice input to be entered before they can begin processing the data, resulting in a lengthy time-lag, which can be a serious drawback in some applications. An obvious solution to this problem is to develop a speech recognition algorithm capable of processing streaming data. Therefore, in this paper we explore the possibility of a streaming, online, ASR system for Japanese using a model based on unidirectional LSTMs trained using connectionist temporal classification (CTC) criteria, with local attention. Such an approach has not been well investigated for use with Japanese, as most Japanese-language ASR systems employ bidirectional networks. The best result for our proposed system during experimental evaluation was a character error rate of 9.87%.","subitem_description_language":"en","subitem_description_type":"Abstract"}]},"item_10001_publisher_8":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"Cambridge University Press","subitem_publisher_language":"en"}]},"item_10001_rights_15":{"attribute_name":"権利情報","attribute_value_mlt":[{"subitem_rights":"This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted re-use, distribution, and reproduction in any medium, provided the original work is properly cited.","subitem_rights_language":"en"}]},"item_10001_source_id_9":{"attribute_name":"収録物ID","attribute_value_mlt":[{"subitem_source_identifier":"20487703","subitem_source_identifier_type":"ISSN"}]},"item_10001_version_type_20":{"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_1715043197608":{"attribute_name":"アクセス権","attribute_value_mlt":[{"subitem_access_right":"open access"}]},"item_1722929371688":{"attribute_name":"出版社版DOI","attribute_value_mlt":[{"subitem_relation_name":[{"subitem_relation_name_language":"ja","subitem_relation_name_text":"10.1017/ATSIP.2020.23"}],"subitem_relation_type_id":{"subitem_relation_type_id_text":"https://doi.org/10.1017/ATSIP.2020.23","subitem_relation_type_select":"DOI"}}]},"item_1723180141928":{"attribute_name":"EID","attribute_value_mlt":[{"subitem_identifier_type":"URI","subitem_identifier_uri":"372885"}]},"item_creator":{"attribute_name":"著者","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Chen, Jiahao","creatorNameLang":"en"}]},{"creatorAffiliations":[{"affiliationNameIdentifiers":[{"affiliationNameIdentifier":"","affiliationNameIdentifierScheme":"ISNI","affiliationNameIdentifierURI":"http://www.isni.org/isni/"}],"affiliationNames":[{"affiliationName":"","affiliationNameLang":"ja"}]}],"creatorNames":[{"creatorName":"西村, 良太","creatorNameLang":"ja"},{"creatorName":"ニシムラ, リョウタ","creatorNameLang":"ja-Kana"},{"creatorName":"Nishimura, Ryota","creatorNameLang":"en"}],"familyNames":[{"familyName":"西村","familyNameLang":"ja"},{"familyName":"ニシムラ","familyNameLang":"ja-Kana"},{"familyName":"Nishimura","familyNameLang":"en"}],"givenNames":[{"givenName":"良太","givenNameLang":"ja"},{"givenName":"リョウタ","givenNameLang":"ja-Kana"},{"givenName":"Ryota","givenNameLang":"en"}],"nameIdentifiers":[{"nameIdentifier":"942","nameIdentifierScheme":"WEKO"},{"nameIdentifier":"346405/profile-ja.html","nameIdentifierScheme":"徳島大学 教育研究者総覧","nameIdentifierURI":"http://pub2.db.tokushima-u.ac.jp/ERD/person/346405/profile-ja.html"}]},{"creatorAffiliations":[{"affiliationNameIdentifiers":[{"affiliationNameIdentifier":"","affiliationNameIdentifierScheme":"ISNI","affiliationNameIdentifierURI":"http://www.isni.org/isni/"}],"affiliationNames":[{"affiliationName":"","affiliationNameLang":"ja"}]}],"creatorNames":[{"creatorName":"北岡, 教英","creatorNameLang":"ja"},{"creatorName":"キタオカ, ノリヒデ","creatorNameLang":"ja-Kana"},{"creatorName":"Kitaoka, Norihide","creatorNameLang":"en"}],"familyNames":[{"familyName":"北岡","familyNameLang":"ja"},{"familyName":"キタオカ","familyNameLang":"ja-Kana"},{"familyName":"Kitaoka","familyNameLang":"en"}],"givenNames":[{"givenName":"教英","givenNameLang":"ja"},{"givenName":"ノリヒデ","givenNameLang":"ja-Kana"},{"givenName":"Norihide","givenNameLang":"en"}],"nameIdentifiers":[{"nameIdentifier":"728","nameIdentifierScheme":"WEKO"},{"nameIdentifier":"10333501","nameIdentifierScheme":"e-Rad","nameIdentifierURI":"https://nrid.nii.ac.jp/ja/search/?qm=10333501"}]}]},"item_files":{"attribute_name":"ファイル情報","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_access","date":[{"dateType":"Available","dateValue":"2021-06-11"}],"displaytype":"detail","filename":"atsip_9_e25.pdf","filesize":[{"value":"421 KB"}],"format":"application/pdf","licensetype":"license_0","mimetype":"application/pdf","url":{"objectType":"fulltext","url":"https://tokushima-u.repo.nii.ac.jp/record/2008800/files/atsip_9_e25.pdf"},"version_id":"84df44dc-17fb-4b2a-8dd4-134e926a0c84"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"CTC","subitem_subject_language":"en","subitem_subject_scheme":"Other"},{"subitem_subject":"Local attention","subitem_subject_language":"en","subitem_subject_scheme":"Other"},{"subitem_subject":"Speech recognition","subitem_subject_language":"en","subitem_subject_scheme":"Other"},{"subitem_subject":"Streaming recognition","subitem_subject_language":"en","subitem_subject_scheme":"Other"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"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":"End-to-end recognition of streaming Japanese speech using CTC and local attention","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"End-to-end recognition of streaming Japanese speech using CTC and local attention","subitem_title_language":"en"}]},"item_type_id":"40001","owner":"7","path":["1713853295607"],"pubdate":{"attribute_name":"PubDate","attribute_value":"2021-06-11"},"publish_date":"2021-06-11","publish_status":"0","recid":"2008800","relation_version_is_last":true,"title":["End-to-end recognition of streaming Japanese speech using CTC and local attention"],"weko_creator_id":"7","weko_shared_id":-1},"updated":"2025-01-28T04:03:14.129741+00:00"}