Skip to main content

Unifying Isolated and Overlapping Audio Event Detection with Multi-Label Multi-Task Convolutional Recurrent Neural Networks

Phan, Huy, Chén, Oliver Y., Koch, Philipp, Pham, Lam Dang, McLoughlin, Ian Vince, Mertins, Afred, De Vos, Maarten (2019) Unifying Isolated and Overlapping Audio Event Detection with Multi-Label Multi-Task Convolutional Recurrent Neural Networks. In: 44th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2019). . IEEE (doi:10.1109/ICASSP.2019.8683064)

PDF - Author's Accepted Manuscript
Download (268kB) Preview
[img]
Preview
Official URL
http://dx.doi.org/10.1109/ICASSP.2019.8683064

Abstract

We propose a multi-label multi-task framework based on a convolutional recurrent neural network to unify detection of isolated and overlapping audio events. The framework leverages the power of convolutional recurrent neural network architectures; convolutional layers learn effective features over which higher recurrent layers perform sequential modelling. Furthermore, the output layer is designed to handle arbitrary degrees of event overlap. At each time step in the recurrent output sequence, an output triple is dedicated to each event category of interest to jointly model event occurrence and temporal boundaries. That is, the network jointly determines whether an event of this category occurs, and when it occurs, by estimating onset and offset positions at each recurrent time step. We then introduce three sequential losses for network training: multi-label classification loss, distance estimation loss, and confidence loss. We demonstrate good generalization on two datasets: ITC-Irst for isolated audio event detection, and TUT-SED-Synthetic-2016 for overlapping audio event detection.

Item Type: Conference or workshop item (Proceeding)
DOI/Identification number: 10.1109/ICASSP.2019.8683064
Uncontrolled keywords: audio event detection, isolated sound, overlapping sound, multi-label, multi-task, convolutional recurrent neural network
Divisions: Faculties > Sciences > School of Computing > Data Science
Depositing User: Huy Phan
Date Deposited: 20 Feb 2019 17:21 UTC
Last Modified: 15 Jan 2020 11:35 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/72657 (The current URI for this page, for reference purposes)
Phan, Huy: https://orcid.org/0000-0003-4096-785X
McLoughlin, Ian Vince: https://orcid.org/0000-0001-7111-2008
  • Depositors only (login required):

Downloads

Downloads per month over past year