1 Ocak 2022 Konferans bildirisi Açık Erişim

Sun, Jianyuan; Liu, Xubo; Mei, Xinhao; Zhao, Jinzheng; Plumbley, Mark D.; Kilic, Volkan; Wang, Wenwu

JSON-LD (schema.org)

{
  "@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"
}