University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Weakly labelled audio tagging via convolutional networks with spatial and channel-wise attention

Hong, Sixin, Zou, Yuexian, Wang, Wenwu and Cao, Meng (2020) Weakly labelled audio tagging via convolutional networks with spatial and channel-wise attention In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2020), May 4 to 8, 2020, Barcelona, Spain.

[img]
Preview
Text
HongZWC_ICASSP_2020.pdf - Accepted version Manuscript

Download (634kB) | Preview

Abstract

Multiple instance learning (MIL) with convolutional neural networks (CNNs) has been proposed recently for weakly labelled audio tagging. However, features from the various CNN filtering channels and spatial regions are often treated equally, which may limit its performance in event prediction. In this paper, we propose a novel attention mechanism, namely, spatial and channel-wise attention (SCA). For spatial attention, we divide it into global and local submodules with the former to capture the event-related spatial regions and the latter to estimate the onset and offset of the events. Considering the variations in CNN channels, channel-wise attention is also exploited to recognize different sound scenes. The proposed SCA can be employed into any CNNs seamlessly with affordable overheads and is end-to-end trainable fashion. Extensive experiments on weakly labelled dataset Audioset show that the proposed SCA with CNNs achieves a state-of-the-art mean average precision (mAP) of 0.390.

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
NameEmailORCID
Hong, Sixin
Zou, Yuexian
Wang, WenwuW.Wang@surrey.ac.uk
Cao, Meng
Date : 24 January 2020
Uncontrolled Keywords : Audio tagging, weakly labelled data, multiple instance learning, spatial attention, channel-wise attention.
Depositing User : James Marshall
Date Deposited : 20 Feb 2020 11:53
Last Modified : 20 Feb 2020 11:53
URI: http://epubs.surrey.ac.uk/id/eprint/853802

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