University of Surrey

Test tubes in the lab Research in the ATI Dance Research

DCASE 2018 Challenge Surrey Cross-task convolutional neural network baseline

Kong, Qiuqiang, Iqbal, Turab, Xu, Yong, Wang, Wenwu and Plumbley, Mark D (2018) DCASE 2018 Challenge Surrey Cross-task convolutional neural network baseline In: DCASE2018 Workshop on Detection and Classification of Acoustic Scenes and Events, 19 - 20 November 2018, Surrey, UK.

[img]
Preview
Text
DCASE 2018 CHALLENGE SURREY CROSS-TASK CONVOLUTIONAL NEURAL NETWORK BASELINE.pdf - Accepted version Manuscript

Download (165kB) | Preview

Abstract

The Detection and Classification of Acoustic Scenes and Events (DCASE) consists of five audio classification and sound event detectiontasks: 1)Acousticsceneclassification,2)General-purposeaudio tagging of Freesound, 3) Bird audio detection, 4) Weakly-labeled semi-supervised sound event detection and 5) Multi-channel audio classification. In this paper, we create a cross-task baseline system for all five tasks based on a convlutional neural network (CNN): a “CNN Baseline” system. We implemented CNNs with 4 layers and 8 layers originating from AlexNet and VGG from computer vision. We investigated how the performance varies from task to task with the same configuration of neural networks. Experiments show that deeper CNN with 8 layers performs better than CNN with 4 layers on all tasks except Task 1. Using CNN with 8 layers, we achieve an accuracy of 0.680 on Task 1, an accuracy of 0.895 and a mean average precision (MAP) of 0.928 on Task 2, an accuracy of 0.751 andanareaunderthecurve(AUC)of0.854onTask3,asoundevent detectionF1scoreof20.8%onTask4,andanF1scoreof87.75%on Task 5. We released the Python source code of the baseline systems under the MIT license for further research.

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
NameEmailORCID
Kong, Qiuqiangq.kong@surrey.ac.uk
Iqbal, Turabt.iqbal@surrey.ac.uk
Xu, Yongyong.xu@surrey.ac.uk
Wang, WenwuW.Wang@surrey.ac.uk
Plumbley, Mark Dm.plumbley@surrey.ac.uk
Date : 2018
Uncontrolled Keywords : DCASE 2018 challenge, convolutional neural networks, open source
Depositing User : Melanie Hughes
Date Deposited : 09 Oct 2018 11:45
Last Modified : 25 Jan 2019 09:40
URI: http://epubs.surrey.ac.uk/id/eprint/849617

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800