Robust audio event recognition with 1-max pooling convolutional neural networks

Huy Phan, Lars Hertel, Marco Maass, Alfred Mertins

5 Citations (Scopus)

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.

Original languageEnglish
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume08-12-September-2016
Pages (from-to)3653-3657
Number of pages5
ISSN2308-457X
DOIs
Publication statusPublished - 01.01.2016

Fingerprint

Dive into the research topics of 'Robust audio event recognition with 1-max pooling convolutional neural networks'. Together they form a unique fingerprint.

Cite this