Konferans bildirisi Açık Erişim
Sun, Jianyuan; Liu, Xubo; Mei, Xinhao; Zhao, Jinzheng; Plumbley, Mark D.; Kilic, Volkan; Wang, Wenwu
<?xml version='1.0' encoding='utf-8'?> <resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd"> <identifier identifierType="DOI">10.48623/aperta.259607</identifier> <creators> <creator> <creatorName>Sun, Jianyuan</creatorName> <givenName>Jianyuan</givenName> <familyName>Sun</familyName> </creator> <creator> <creatorName>Liu, Xubo</creatorName> <givenName>Xubo</givenName> <familyName>Liu</familyName> <affiliation>Univ Surrey, Ctr Vis Speech & Signal Proc CVSSP, Surrey, England</affiliation> </creator> <creator> <creatorName>Mei, Xinhao</creatorName> <givenName>Xinhao</givenName> <familyName>Mei</familyName> <affiliation>Univ Surrey, Ctr Vis Speech & Signal Proc CVSSP, Surrey, England</affiliation> </creator> <creator> <creatorName>Zhao, Jinzheng</creatorName> <givenName>Jinzheng</givenName> <familyName>Zhao</familyName> <affiliation>Univ Surrey, Ctr Vis Speech & Signal Proc CVSSP, Surrey, England</affiliation> </creator> <creator> <creatorName>Plumbley, Mark D.</creatorName> <givenName>Mark D.</givenName> <familyName>Plumbley</familyName> <affiliation>Univ Surrey, Ctr Vis Speech & Signal Proc CVSSP, Surrey, England</affiliation> </creator> <creator> <creatorName>Kilic, Volkan</creatorName> <givenName>Volkan</givenName> <familyName>Kilic</familyName> <affiliation>Izmir Katip Celebi Univ, Dept Elect & Elect Engn, Izmir, Turkey</affiliation> </creator> <creator> <creatorName>Wang, Wenwu</creatorName> <givenName>Wenwu</givenName> <familyName>Wang</familyName> <affiliation>Univ Surrey, Ctr Vis Speech & Signal Proc CVSSP, Surrey, England</affiliation> </creator> </creators> <titles> <title>Deep Neural Decision Forest For Acoustic Scene Classification</title> </titles> <publisher>Aperta</publisher> <publicationYear>2022</publicationYear> <dates> <date dateType="Issued">2022-01-01</date> </dates> <resourceType resourceTypeGeneral="Text">Conference paper</resourceType> <alternateIdentifiers> <alternateIdentifier alternateIdentifierType="url">https://aperta.ulakbim.gov.tr/record/259607</alternateIdentifier> </alternateIdentifiers> <relatedIdentifiers> <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.48623/aperta.259606</relatedIdentifier> </relatedIdentifiers> <rightsList> <rights rightsURI="http://www.opendefinition.org/licenses/cc-by">Creative Commons Attribution</rights> <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights> </rightsList> <descriptions> <description descriptionType="Abstract">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.</description> </descriptions> </resource>
Tüm sürümler | Bu sürüm | |
---|---|---|
Görüntülenme | 13 | 13 |
İndirme | 2 | 2 |
Veri hacmi | 410 Bytes | 410 Bytes |
Tekil görüntülenme | 13 | 13 |
Tekil indirme | 2 | 2 |