{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00218424","sets":["1164:5064:10822:10948"]},"path":["10948"],"owner":"44499","recid":"218424","title":["音響シーン識別のための注目すべき音を自動検出するニューラルビームフォーマの検討"],"pubdate":{"attribute_name":"公開日","attribute_value":"2022-06-10"},"_buckets":{"deposit":"4c1a583b-9b9f-4d9b-9e53-6ebabbbcab28"},"_deposit":{"id":"218424","pid":{"type":"depid","value":"218424","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"音響シーン識別のための注目すべき音を自動検出するニューラルビームフォーマの検討","author_link":["567927","567932","567929","567928","567930","567931"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"音響シーン識別のための注目すべき音を自動検出するニューラルビームフォーマの検討"},{"subitem_title":"Neural Beamformer with Automatic Detection of Notable Sounds for Acoustic Scene Classification","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2","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2022-06-10","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"筑波大学大学院システム情報工学研究群"},{"subitem_text_value":"筑波大学大学院システム情報工学研究群"},{"subitem_text_value":"早稲田大学大学院情報生産システム研究科/筑波大学大学院システム情報工学研究群"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Degree Programs in Systems and Information Engineering, University of Tsukuba","subitem_text_language":"en"},{"subitem_text_value":"Degree Programs in Systems and Information Engineering, University of Tsukuba","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information, Production and Systems, Waseda University / Degree Programs in Systems and Information Engineering, University of Tsukuba","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/218424/files/IPSJ-MUS22134032.pdf","label":"IPSJ-MUS22134032.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-MUS22134032.pdf","filesize":[{"value":"3.0 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"21"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"e105d858-8385-4eaa-8c1c-9398c5b36a59","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2022 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":"市川, 創大"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"山田, 武志"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"牧野, 昭二"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Sota, Ichikawa","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Takeshi, Yamada","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shoji, Makino","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10438388","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":"2188-8752","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"近年,マルチチャネル信号を入力とするビームフォーマを用いた音響シーン識別手法が提案されている.一般にビームフォーマの空間フィルタ(指向特性)を決定するためには,目的音方向などの事前情報が必要となる.しかし,個々の音響シーンにおいて注目すべき音がそもそもどんな音であり,またその音がどの方向にあるのかは自明ではないため,前処理としてビームフォーマを適用することは難しいと考えられる.これまでに我々は,空間フィルタ生成器と識別器のネットワークを連結し,同時最適化するというアプローチを検討している.このアプローチの狙いは,注目すべき音がどんな音なのかを自動的に学習し,またそれを強調するための空間フィルタを自動的に生成することにあり,学習の際には目的音の方向や教師信号といった事前情報を一切必要としない.本稿では,MVDR(MinimumVariance Distortionless Response)ビームフォーマのアイデアを取り入れた損失関数を提案し,実験によってその有効性を検証する.","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Recently, acoustic scene classification using a beamformer with multi-channel signals as input has been proposed. Generally, prior information such as the direction of arrival of the target sound is necessary to generate the spatial filter of the beamformer. However, it is difficult to apply a beamformer as a pre-processing method because it is not obvious what kind of sound is of interest in a particular acoustic scene and in which direction the sound is located. We have devised an approach in which the networks of a spatial filter generator and classifier are concatenated and simultaneously optimized. The goal of this approach is to automatically learn what sounds to be focused on and automatically generate spatial filters to emphasize them, without requiring any prior information such as the direction of arrival of the target sound or a reference signal. This paper proposes a loss function that incorporates the idea of the MVDR (Minimum Variance Distortionless Response) beamformer and verifies its effectiveness through experiments.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告音楽情報科学(MUS)"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2022-06-10","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"32","bibliographicVolumeNumber":"2022-MUS-134"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":218424,"updated":"2025-01-19T15:09:58.885601+00:00","links":{},"created":"2025-01-19T01:18:47.660908+00:00"}