Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification

TL;DR

This paper introduces a deep CNN architecture for environmental sound classification and demonstrates that data augmentation significantly enhances performance, achieving state-of-the-art results by addressing data scarcity issues.

Contribution

The study proposes a novel deep CNN model combined with audio data augmentation techniques to improve environmental sound classification accuracy.

Findings

Data augmentation improves CNN performance significantly.

Deep CNN outperforms shallow models with augmentation.

Different augmentations affect class accuracy uniquely.

Abstract

The ability of deep convolutional neural networks (CNN) to learn discriminative spectro-temporal patterns makes them well suited to environmental sound classification. However, the relative scarcity of labeled data has impeded the exploitation of this family of high-capacity models. This study has two primary contributions: first, we propose a deep convolutional neural network architecture for environmental sound classification. Second, we propose the use of audio data augmentation for overcoming the problem of data scarcity and explore the influence of different augmentations on the performance of the proposed CNN architecture. Combined with data augmentation, the proposed model produces state-of-the-art results for environmental sound classification. We show that the improved performance stems from the combination of a deep, high-capacity model and an augmented training set: this combination outperforms both the proposed CNN without augmentation and a "shallow" dictionary learning model with augmentation. Finally, we examine the influence of each augmentation on the model's classification accuracy for each class, and observe that the accuracy for each class is influenced differently by each augmentation, suggesting that the performance of the model could be improved further by applying class-conditional data augmentation.