{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00108570","sets":["6504:6505:7806"]},"path":["7806"],"owner":"6748","recid":"108570","title":["Audio-visual musical instrument recognition"],"pubdate":{"attribute_name":"公開日","attribute_value":"2011-03-02"},"_buckets":{"deposit":"2e1794f0-1f2f-4644-ac8b-0bee283c8159"},"_deposit":{"id":"108570","pid":{"type":"depid","value":"108570","revision_id":0},"owners":[6748],"status":"published","created_by":6748},"item_title":"Audio-visual musical instrument recognition","author_link":["20849","20850","20852","20853","20851"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Audio-visual musical instrument recognition"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"人工知能と認知科学","subitem_subject_scheme":"Other"}]},"item_type_id":"22","publish_date":"2011-03-02","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"item_22_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"京大"},{"subitem_text_value":"ホンダ Research Institute Japan"},{"subitem_text_value":"ホンダ Research Institute Japan"},{"subitem_text_value":"京大"},{"subitem_text_value":"京大"}]},"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/108570/files/IPSJ-Z73-5R-9.pdf"},"date":[{"dateType":"Available","dateValue":"2014-12-17"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-Z73-5R-9.pdf","filesize":[{"value":"928.8 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"d6eae486-e007-4650-a871-4e2ef964fef8","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2011 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"AngelicaLim"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"中村圭佑"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"中臺一博"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"尾形哲也"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"奥乃博"}],"nameIdentifiers":[{}]}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_5794","resourcetype":"conference paper"}]},"item_22_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00349328","subitem_source_identifier_type":"NCID"}]},"item_22_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"Is this person playing a violin or a flute? Classification of musical instrument performances is usually carried out using audio features such as spectral coefficients. We propose augmenting the typical audio feature set with visual features. We show that a combination of audio features and video perform better than audio alone, and verify this multimodal recognition approach on a real-time robot platform.","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"310","bibliographic_titles":[{"bibliographic_title":"第73回全国大会講演論文集"}],"bibliographicPageStart":"309","bibliographicIssueDates":{"bibliographicIssueDate":"2011-03-02","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2011"}]},"relation_version_is_last":true,"weko_creator_id":"6748"},"id":108570,"updated":"2025-01-21T08:44:55.281800+00:00","links":{},"created":"2025-01-18T23:51:08.999300+00:00"}