{"created":"2024-11-13T08:36:08.535457+00:00","id":2000359,"links":{},"metadata":{"_buckets":{"deposit":"ecdf4084-35a8-49b3-a0d7-f1c48ec3967e"},"_deposit":{"created_by":25,"id":"2000359","owner":"25","owners":[25],"pid":{"revision_id":0,"type":"depid","value":"2000359"},"status":"published"},"_oai":{"id":"oai:repository.ninjal.ac.jp:02000359","sets":["245:1731477595303"]},"author_link":[],"item_10003_biblio_info_32":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"2024","bibliographicIssueDateType":"Issued"},"bibliographicNumberOfPages":"11","bibliographicPageEnd":"112","bibliographicPageStart":"102","bibliographicVolumeNumber":"1","bibliographic_titles":[{"bibliographic_title":"言語資源ワークショップ発表論文集","bibliographic_titleLang":"ja"},{"bibliographic_title":"Proceedings of Language Resources Workshop","bibliographic_titleLang":"en"}]}]},"item_10003_description_27":{"attribute_name":"会議概要（会議名, 開催地, 会期, 主催者等）","attribute_value_mlt":[{"subitem_description":"会議名: 言語資源ワークショップ2024, 開催地: オンライン, 会期: 2024年8月28日-29日, 主催: 国立国語研究所 言語資源開発センター, 共催: 言語資源協会, 後援: 国立情報学研究所","subitem_description_language":"ja","subitem_description_type":"Other"}]},"item_10003_description_29":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"動画共有サイトにアップロードされている中国語の動画は，字幕が画像データとして動画のフレーム内に埋め込まれていることが圧倒的である．そのため，動画からテキストを抽出し，コーパスを作成する際には，文字認識あるいは音声認識の手法を用いる必要がある．日本において，中国人母語話者が日常的に話している言葉を集めたコーパスは多いとは言えず，その多くは中国語学習者用に作られている．我々の研究では，中国人母語話者の使用まで射程にいれ，言語研究に耐えうるようなコーパスの作成を目指す．さらに，字幕に対するOCR,音声に対する音声認識，動画制作者が用意した字幕など，複数のリソースから得られたテキストを，同時に表示するようなアプリケーションを実装する．","subitem_description_language":"ja","subitem_description_type":"Abstract"}]},"item_10003_description_43":{"attribute_name":"フォーマット","attribute_value_mlt":[{"subitem_description":"application/pdf","subitem_description_language":"ja","subitem_description_type":"Other"}]},"item_10003_description_51":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_description":"大阪大学人文学研究科","subitem_description_language":"ja","subitem_description_type":"Other"},{"subitem_description":"大阪大学人文学研究科","subitem_description_language":"ja","subitem_description_type":"Other"},{"subitem_description":"大阪大学人文学研究科","subitem_description_language":"ja","subitem_description_type":"Other"}]},"item_10003_description_52":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_description":"Osaka University Graduate School of Humanites","subitem_description_language":"en","subitem_description_type":"Other"},{"subitem_description":"Osaka University Graduate School of Humanites","subitem_description_language":"en","subitem_description_type":"Other"},{"subitem_description":"Osaka University Graduate School of Humanites","subitem_description_language":"en","subitem_description_type":"Other"}]},"item_10003_identifier_registration":{"attribute_name":"ID登録","attribute_value_mlt":[{"subitem_identifier_reg_text":"10.15084/0002000359","subitem_identifier_reg_type":"JaLC"}]},"item_10003_publisher_45":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"国立国語研究所","subitem_publisher_language":"ja"}]},"item_10003_relation_40":{"attribute_name":"関連サイト","attribute_value_mlt":[{"subitem_relation_name":[{"subitem_relation_name_language":"ja","subitem_relation_name_text":"言語資源ワークショップ2024"}],"subitem_relation_type":"isSupplementedBy","subitem_relation_type_id":{"subitem_relation_type_id_text":"https://clrd.ninjal.ac.jp/lrw2024.html","subitem_relation_type_select":"URI"}}]},"item_10003_version_type_44":{"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_creator":{"attribute_name":"著者","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"篠崎, 秀紀","creatorNameLang":"ja"},{"creatorName":"Shinozaki, Hidenori","creatorNameLang":"en"}]},{"creatorNames":[{"creatorName":"于, 拙","creatorNameLang":"ja"},{"creatorName":"Yu, Zhuo","creatorNameLang":"en"}]},{"creatorNames":[{"creatorName":"陳, 宇鍇","creatorNameLang":"ja"},{"creatorName":"Chen, Yukai","creatorNameLang":"en"}]}]},"item_files":{"attribute_name":"ファイル情報","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_date","date":[{"dateType":"Available","dateValue":"2024-11-13"}],"displaytype":"detail","filename":"LRW2024_08-o07s.pdf","filesize":[{"value":"4.9 MB"}],"format":"application/pdf","mimetype":"application/pdf","url":{"label":"LRW2024_08-o07s.pdf","url":"https://repository.ninjal.ac.jp/record/2000359/files/LRW2024_08-o07s.pdf"},"version_id":"5be0c58e-8e38-41ff-9c29-2a31b379fbaa"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"コーパス","subitem_subject_language":"ja","subitem_subject_scheme":"Other"},{"subitem_subject":"中国語","subitem_subject_language":"ja","subitem_subject_scheme":"Other"},{"subitem_subject":"corpus","subitem_subject_language":"en","subitem_subject_scheme":"Other"},{"subitem_subject":"Chines","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":"conference paper","resourceuri":"http://purl.org/coar/resource_type/c_5794"}]},"item_title":"『中国語動画音声コーパス』の構築 : 複数モダリティによる正確な書き起こしを目指して","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"『中国語動画音声コーパス』の構築 : 複数モダリティによる正確な書き起こしを目指して","subitem_title_language":"ja"},{"subitem_title":"The Construction of a Chinese Video-Audio Corpus : Aiming for Accurate Transcription through Multiple Modalities","subitem_title_language":"en"}]},"item_type_id":"10003","owner":"25","path":["1731477595303"],"pubdate":{"attribute_name":"PubDate","attribute_value":"2024-11-13"},"publish_date":"2024-11-13","publish_status":"0","recid":"2000359","relation_version_is_last":true,"title":["『中国語動画音声コーパス』の構築 : 複数モダリティによる正確な書き起こしを目指して"],"weko_creator_id":"25","weko_shared_id":-1},"updated":"2024-11-14T05:51:12.584717+00:00"}