{"updated":"2025-01-19T09:42:27.610363+00:00","links":{},"created":"2025-01-19T01:36:38.361140+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00234740","sets":["1164:5159:11541:11627"]},"path":["11627"],"owner":"44499","recid":"234740","title":["Enhancing Feature Integration to Improve Classification Accuracy of Similar Categories in Acoustic Scene Classification"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-06-07"},"_buckets":{"deposit":"735489d3-e76e-415f-8b8b-01816c6567b4"},"_deposit":{"id":"234740","pid":{"type":"depid","value":"234740","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Enhancing Feature Integration to Improve Classification Accuracy of Similar Categories in Acoustic Scene Classification","author_link":["640058","640061","640059","640062","640060","640057"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Enhancing Feature Integration to Improve Classification Accuracy of Similar Categories in Acoustic Scene Classification"},{"subitem_title":"Enhancing Feature Integration to Improve Classification Accuracy of Similar Categories in 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":"2024-06-07","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"The University of Tokyo"},{"subitem_text_value":"The University of Tokyo"},{"subitem_text_value":"The University of Tokyo"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"The University of Tokyo","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"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/234740/files/IPSJ-SLP24152053.pdf","label":"IPSJ-SLP24152053.pdf"},"date":[{"dateType":"Available","dateValue":"2026-06-07"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP24152053.pdf","filesize":[{"value":"5.0 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"22"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"18bdb607-c332-460b-9875-5ffbfce5e410","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Shuting, Hao"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Daisuke, Saito"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Nobuaki, Minematsu"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Shuting, Hao","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Daisuke, Saito","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Nobuaki, Minematsu","creatorNameLang":"en"}],"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":"This study focuses on Acoustic Scene Classification (ASC), which categorizes environmental audio streams into predefined semantic labels. We introduce a novel architecture that integrates multi-layer classifiers and direct finetuning, presenting a new perspective in ASC research. The study employs the TAU Urban Acoustic Scenes 2022 Mobile dataset for fine-tuning and validation. We utilized the SSAST model, pre-trained on the AudioSet and LibriSpeech datasets, and fine-tuned it on the TAU dataset with a unique approach to enhance ASC-specific feature learning. Our layered SSAST system achieved an accuracy of 52.17% and an AUC of 88.66% in ASC, marking a notable improvement over the baseline with absolute increases of 0.99% in accuracy and 0.85% in AUC.","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"This study focuses on Acoustic Scene Classification (ASC), which categorizes environmental audio streams into predefined semantic labels. We introduce a novel architecture that integrates multi-layer classifiers and direct finetuning, presenting a new perspective in ASC research. The study employs the TAU Urban Acoustic Scenes 2022 Mobile dataset for fine-tuning and validation. We utilized the SSAST model, pre-trained on the AudioSet and LibriSpeech datasets, and fine-tuned it on the TAU dataset with a unique approach to enhance ASC-specific feature learning. Our layered SSAST system achieved an accuracy of 52.17% and an AUC of 88.66% in ASC, marking a notable improvement over the baseline with absolute increases of 0.99% in accuracy and 0.85% in AUC.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"5","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":"53","bibliographicVolumeNumber":"2024-SLP-152"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":234740}