{"id":234721,"updated":"2025-01-19T09:42:50.584523+00:00","links":{},"created":"2025-01-19T01:36:36.576882+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00234721","sets":["1164:5159:11541:11627"]},"path":["11627"],"owner":"44499","recid":"234721","title":["リアルタイムに動作する方向と声の特徴を利用した目標音抽出"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-06-07"},"_buckets":{"deposit":"48c08a16-3615-42ed-88b9-4dc6003de9df"},"_deposit":{"id":"234721","pid":{"type":"depid","value":"234721","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"リアルタイムに動作する方向と声の特徴を利用した目標音抽出","author_link":["639980","639976","639979","639977","639978"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"リアルタイムに動作する方向と声の特徴を利用した目標音抽出"},{"subitem_title":"Real-time target speaker extraction using direction and voice features\\n","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"ポスターセッション1","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2024-06-07","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"京セラ株式会社"},{"subitem_text_value":"京セラ株式会社"},{"subitem_text_value":"京セラ株式会社"},{"subitem_text_value":"京セラ株式会社"},{"subitem_text_value":"京セラ株式会社"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Kyocera","subitem_text_language":"en"},{"subitem_text_value":"Kyocera","subitem_text_language":"en"},{"subitem_text_value":"Kyocera","subitem_text_language":"en"},{"subitem_text_value":"Kyocera","subitem_text_language":"en"},{"subitem_text_value":"Kyocera","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"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/234721/files/IPSJ-SLP24152034.pdf","label":"IPSJ-SLP24152034.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP24152034.pdf","filesize":[{"value":"1.3 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"22"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"e1cb5c7e-c279-4c5b-ad31-95692b0abbf2","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Institute of Electronics, Information and Communication Engineers This SIG report is only available to those in membership of the SIG."}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"大原, 健悟"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"大角, 耕介"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"山本, 絵里香"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"諸菱, 正典"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"荒川, 隆行"}],"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_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8663","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"本研究では，汎用のスマートフォン上でリアルタイムに動作する，方向と声の特徴を利用した目標音抽出を提案する．深層学習ネットワークサイズの削減と，高速化ライブラリで実行できる形式へのコンバートを行う．また，目標音の話者をユーザに選択させ，その方向と対応する声の特徴を利用した目標音抽出を行う．評価として，処理単位が小さくてもリアルタイムファクタが 0.549 まで低下してリアルタイムで処理可能になること，また，同性, 背景雑音ありでも目標音抽出性能が最大で 8.7dB まで向上することを示す．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告音声言語情報処理（SLP）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2024-06-07","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"34","bibliographicVolumeNumber":"2024-SLP-152"}]},"relation_version_is_last":true,"weko_creator_id":"44499"}}