University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Sample mixed-based data augmentation for domestic audio tagging

Wei, Shengyun, Xu, Kele, Wang, Dezhi, Liao, Feifan, Wang, Huaimin and Kong, Qiuqiang (2018) Sample mixed-based data augmentation for domestic audio tagging In: DCASE 2018 Workshop on Detection and Classification of Acoustic Scenes and Events, 19 -20 November 2018, Surrey, UK.

[img]
Preview
Text
SAMPLE MIXED-BASED DATA AUGMENTATION FOR DOMESTIC AUDIO TAGGING.pdf - Accepted version Manuscript

Download (494kB) | Preview

Abstract

Audio tagging has attracted increasing attention since last decade and has various potential applications in many fields. The objective of audio tagging is to predict the labels of an audio clip. Recently deep learning methods have been applied to audio tagging and have achieved state-of-the-art performance, which provides a poor generalization ability on new data. However due to the limited size of audio tagging data such as DCASE data, the trained models tend to result in overfitting of the network. Previous data augmentation methods such as pitch shifting, time stretching and adding background noise do not show much improvement in audio tagging. In this paper, we explore the sample mixed data augmentation for the domestic audio tagging task, including mixup, SamplePairing and extrapolation. We apply a convolutional recurrent neural network (CRNN) with attention module with log-scaled mel spectrum as a baseline system. In our experiments, we achieve an state-of-the-art of equal error rate (EER) of 0.10 on DCASE 2016 task4 dataset with mixup approach, outperforming the baseline system without data augmentation.

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
NameEmailORCID
Wei, Shengyun
Xu, Kele
Wang, Dezhi
Liao, Feifan
Wang, Huaimin
Kong, Qiuqiangq.kong@surrey.ac.uk
Date : 2018
Uncontrolled Keywords : Audio tagging, data augmentation, sample mixed, convolutional recurrent neural network
Depositing User : Melanie Hughes
Date Deposited : 10 Oct 2018 08:18
Last Modified : 19 Nov 2018 02:08
URI: http://epubs.surrey.ac.uk/id/eprint/849628

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