University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Audio set classification with attention model: a probabilistic perspective

Kong, Qiuqiang, Xu, Yong, Wang, Wenwu and Plumbley, Mark (2018) Audio set classification with attention model: a probabilistic perspective In: ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 15 - 20 Apr 2018, Calgary, Canada.

[img] Text
ICASSP2018_audioset_v0.8.pdf - Accepted version Manuscript
Restricted to Repository staff only until 21 April 2018.

Download (1MB)


This paper investigates the Audio Set classification. Audio Set is a large scale weakly labelled dataset (WLD) of audio clips. In WLD only the presence of a label is known, without knowing the happening time of the labels. We propose an attention model to solve this WLD problem and explain the attention model from a novel probabilistic perspective. Each audio clip in Audio Set consists of a collection of features. We call each feature as an instance and the collection as a bag following the terminology in multiple instance learning. In the attention model, each instance in the bag has a trainable probability measure for each class. The classification of the bag is the expectation of the classification output of the instances in the bag with respect to the learned probability measure. Experiments show that the proposed attention model achieves a mAP of 0.327 on Audio Set, outperforming the Google’s baseline of 0.314.

Item Type: Conference or Workshop Item (Conference Poster)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
Date : 2018
Funders : EPSRC
Copyright Disclaimer : © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
Uncontrolled Keywords : Audio Set, audio classification, attention model, multiple instance learning.
Depositing User : Melanie Hughes
Date Deposited : 13 Mar 2018 09:21
Last Modified : 13 Mar 2018 09:21

Actions (login required)

View Item View Item


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