University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Fast Tagging of Natural Sounds Using Marginal Co-regularization

Huang, Q, Xu, Y, Jackson, PJB, Wang, W and Plumbley, MD (2017) Fast Tagging of Natural Sounds Using Marginal Co-regularization In: ICASSP2017, The 42nd IEEE International Conference on Acoustics, Speech and Signal Processing, 2017-03-05 - 2017-03-09, New Orleans, USA.

[img]
Preview
Text
QH11.pdf - Accepted version Manuscript
Available under License : See the attached licence file.

Download (309kB) | Preview
[img]
Preview
PDF (licence)
SRI_deposit_agreement.pdf
Available under License : See the attached licence file.

Download (33kB) | Preview

Abstract

Automatic and fast tagging of natural sounds in audio collections is a very challenging task due to wide acoustic variations, the large number of possible tags, the incomplete and ambiguous tags provided by different labellers. To handle these problems, we use a co-regularization approach to learn a pair of classifiers on sound and text. The first classifier maps low-level audio features to a true tag list. The second classifier maps actively corrupted tags to the true tags, reducing incorrect mappings caused by low-level acoustic variations in the first classifier, and to augment the tags with additional relevant tags. Training the classifiers is implemented using marginal co-regularization, pair of which draws the two classifiers into agreement by a joint optimization. We evaluate this approach on two sound datasets, Freefield1010 and Task4 of DCASE2016. The results obtained show that marginal co-regularization outperforms the baseline GMM in both ef- ficiency and effectiveness.

Item Type: Conference or Workshop Item (Conference Poster)
Subjects : Electronic Engineering
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
AuthorsEmailORCID
Huang, QUNSPECIFIEDUNSPECIFIED
Xu, YUNSPECIFIEDUNSPECIFIED
Jackson, PJBUNSPECIFIEDUNSPECIFIED
Wang, WUNSPECIFIEDUNSPECIFIED
Plumbley, MDUNSPECIFIEDUNSPECIFIED
Date : 2017
Copyright Disclaimer : © 2017 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.
Contributors :
ContributionNameEmailORCID
UNSPECIFIEDIEEE, UNSPECIFIEDUNSPECIFIED
Uncontrolled Keywords : natural sound, annotation, co-regularization
Depositing User : Symplectic Elements
Date Deposited : 16 Dec 2016 14:51
Last Modified : 16 Dec 2016 14:51
URI: http://epubs.surrey.ac.uk/id/eprint/813129

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