Skip to main content

Robust Audio Event Recognition with 1-Max Pooling Convolutional Neural Networks

Phan, Huy, Hertel, Lars, Maass, Marco, Mertins, Alfred (2016) Robust Audio Event Recognition with 1-Max Pooling Convolutional Neural Networks. In: Proceedings of Interspeech. . pp. 3653-3657. ISCA, San Francisco, USA (doi:10.21437/Interspeech.2016-123) (KAR id:72681)

PDF Author's Accepted Manuscript
Language: English
Download (171kB) Preview
[img]
Preview
Official URL
http://dx.doi.org/10.21437/Interspeech.2016-123

Abstract

We present in this paper a simple, yet efficient convolutional neural network (CNN) architecture for robust audio event recognition. Opposing to deep CNN architectures with multiple convolutional and pooling layers topped up with multiple fully connected layers, the proposed network consists of only three layers: convolutional, pooling, and softmax layer. Two further features distinguish it from the deep architectures that have been proposed for the task: varying-size convolutional filters at the convolutional layer and 1-max pooling scheme at the pooling layer. In intuition, the network tends to select the most discriminative features from the whole audio signals for recognition. Our proposed CNN not only shows state-of-the-art performance on the standard task of robust audio event recognition but also outperforms other deep architectures up to 4.5% in terms of recognition accuracy, which is equivalent to 76.3% relative error reduction.

Item Type: Conference or workshop item (Proceeding)
DOI/Identification number: 10.21437/Interspeech.2016-123
Uncontrolled keywords: audio event recognition, robustness, convolutional neural networks, 1-max pooling
Divisions: Faculties > Sciences > School of Computing
Depositing User: Huy Phan
Date Deposited: 25 Feb 2019 16:10 UTC
Last Modified: 15 Jan 2020 12:14 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/72681 (The current URI for this page, for reference purposes)
Phan, Huy: https://orcid.org/0000-0003-4096-785X
  • Depositors only (login required):

Downloads

Downloads per month over past year