University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Orthogonality-regularized masked NMF for learning on weakly labeled audio data

Sobieraj, Iwona, Rencker, Lucas and Plumbley, Mark D (2018) Orthogonality-regularized masked NMF for learning on weakly labeled audio data In: IEEE ICASSP 2018, 15 - 20 April 2018, Calgary, Alberta, Canada.

[img]
Preview
Text
orthogonality-regularized-masked (5).pdf - Accepted version Manuscript

Download (165kB) | Preview

Abstract

Non-negative Matrix Factorization (NMF) is a well established tool for audio analysis. However, it is not well suited for learning on weakly labeled data, i.e. data where the exact timestamp of the sound of interest is not known. In this paper we propose a novel extension to NMF, that allows it to extract meaningful representations from weakly labeled audio data. Recently, a constraint on the activation matrix was proposed to adapt for learning on weak labels. To further improve the method we propose to add an orthogonality regularizer of the dictionary in the cost function of NMF. In that way we obtain appropriate dictionaries for the sounds of interest and background sounds from weakly labeled data. We demonstrate that the proposed Orthogonality-Regularized Masked NMF (ORM-NMF) can be used for Audio Event Detection of rare events and evaluate the method on the development data from Task2 of DCASE2017 Challenge.

Item Type: Conference or Workshop Item (Conference Poster)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
NameEmailORCID
Sobieraj, Iwonai.sobieraj@surrey.ac.uk
Rencker, Lucaslucas.rencker@surrey.ac.uk
Plumbley, Mark Dm.plumbley@surrey.ac.uk
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 : Non-negative Matrix Factorization, weakly labeled data, Acoustic Event Detection
Depositing User : Melanie Hughes
Date Deposited : 11 Apr 2018 10:24
Last Modified : 18 Apr 2018 07:47
URI: http://epubs.surrey.ac.uk/id/eprint/846172

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