Acoustic Event Detection from Weakly Labeled Data Using Auditory Salience

Podwinska, Z, Sobieraj, I, Fazenda, BM ORCID: https://orcid.org/0000-0002-3912-0582, Davies, WJ ORCID: https://orcid.org/0000-0002-5835-7489 and Plumbley, MD 2019, Acoustic Event Detection from Weakly Labeled Data Using Auditory Salience , in: 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 12-17 May 2019, Brighton, UK.

[img]
Preview
PDF (Accepted manuscript) - Accepted Version
Download (350kB) | Preview

Abstract

Acoustic Event Detection (AED) is an important task of machine listening which, in recent years, has been addressed using common machine learning methods like Non-negative Matrix Factorization (NMF) or deep learning. However, most of these approaches do not take into consideration the way that human auditory system detects salient sounds. In this work, we propose a method for AED using weakly labeled data that combines a Non-negative Matrix Factorization model with a salience model based on predictive coding in the form of Kalman filters. We show that models of auditory perception, particularly auditory salience, can be successfully incorporated into existing AED methods and improve their performance on rare event detection. We evaluate the method on the Task2 of DCASE2017 Challenge.

Item Type: Conference or Workshop Item (Paper)
Schools: Schools > School of Computing, Science and Engineering
Journal or Publication Title: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Publisher: IEEE
Funders: Engineering and Physical Sciences Research Council (EPSRC), European Union
Depositing User: ZUZANNA Podwinska
Date Deposited: 07 May 2019 08:59
Last Modified: 30 Sep 2019 08:09
URI: http://usir.salford.ac.uk/id/eprint/51244

Actions (login required)

Edit record (repository staff only) Edit record (repository staff only)

Downloads

Downloads per month over past year