Konferans bildirisi Açık Erişim
Sun, Jianyuan; Liu, Xubo; Mei, Xinhao; Zhao, Jinzheng; Plumbley, Mark D.; Kilic, Volkan; Wang, Wenwu
{ "@context": "https://schema.org/", "@id": 259607, "@type": "ScholarlyArticle", "creator": [ { "@type": "Person", "name": "Sun, Jianyuan" }, { "@type": "Person", "affiliation": "Univ Surrey, Ctr Vis Speech & Signal Proc CVSSP, Surrey, England", "name": "Liu, Xubo" }, { "@type": "Person", "affiliation": "Univ Surrey, Ctr Vis Speech & Signal Proc CVSSP, Surrey, England", "name": "Mei, Xinhao" }, { "@type": "Person", "affiliation": "Univ Surrey, Ctr Vis Speech & Signal Proc CVSSP, Surrey, England", "name": "Zhao, Jinzheng" }, { "@type": "Person", "affiliation": "Univ Surrey, Ctr Vis Speech & Signal Proc CVSSP, Surrey, England", "name": "Plumbley, Mark D." }, { "@type": "Person", "affiliation": "Izmir Katip Celebi Univ, Dept Elect & Elect Engn, Izmir, Turkey", "name": "Kilic, Volkan" }, { "@type": "Person", "affiliation": "Univ Surrey, Ctr Vis Speech & Signal Proc CVSSP, Surrey, England", "name": "Wang, Wenwu" } ], "datePublished": "2022-01-01", "description": "Acoustic scene classification (ASC) aims to classify an audio clip based on the characteristic of the recording environment. In this regard, deep learning based approaches have emerged as a useful tool for ASC problems. Conventional approaches to improving the classification accuracy include integrating auxiliary methods such as attention mechanism, pre-trained models and ensemble multiple sub-networks. However, due to the complexity of audio clips captured from different environments, it is difficult to distinguish their categories without using any auxiliary methods for existing deep learning models using only a single classifier. In this paper, we propose a novel approach for ASC using deep neural decision forest (DNDF). DNDF combines a fixed number of convolutional layers and a decision forest as the final classifier. The decision forest consists of a fixed number of decision tree classifiers, which have been shown to offer better classification performance than a single classifier in some datasets. In particular, the decision forest differs substantially from traditional random forests as it is stochastic, differentiable, and capable of using the back-propagation to update and learn feature representations in neural network. Experimental results on the DCASE2019 and ESC-50 datasets demonstrate that our proposed DNDF method improves the ASC performance in terms of classification accuracy and shows competitive performance as compared with state-of-the-art baselines.", "headline": "Deep Neural Decision Forest for Acoustic Scene Classification", "identifier": 259607, "image": "https://aperta.ulakbim.gov.tr/static/img/logo/aperta_logo_with_icon.svg", "license": "http://www.opendefinition.org/licenses/cc-by", "name": "Deep Neural Decision Forest for Acoustic Scene Classification", "url": "https://aperta.ulakbim.gov.tr/record/259607" }
Tüm sürümler | Bu sürüm | |
---|---|---|
Görüntülenme | 13 | 13 |
İndirme | 2 | 2 |
Veri hacmi | 410 Bytes | 410 Bytes |
Tekil görüntülenme | 13 | 13 |
Tekil indirme | 2 | 2 |