DD-CNN: Depthwise Disout Convolutional Neural Network for Low-complexity Acoustic Scene Classification

TL;DR

This paper introduces DD-CNN, a low-complexity neural network using depthwise separable convolutions, SpecAugment, and Disout for efficient urban acoustic scene classification, achieving high accuracy with reduced complexity.

Contribution

The paper proposes a novel DD-CNN architecture that combines depthwise separable convolutions with data augmentation and regularization techniques for improved acoustic scene classification.

Findings

Achieved 92.04% accuracy on DCASE2020 validation set.

Reduced network complexity while maintaining high classification performance.

Effective learning of discriminative acoustic features from audio fragments.

Abstract

This paper presents a Depthwise Disout Convolutional Neural Network (DD-CNN) for the detection and classification of urban acoustic scenes. Specifically, we use log-mel as feature representations of acoustic signals for the inputs of our network. In the proposed DD-CNN, depthwise separable convolution is used to reduce the network complexity. Besides, SpecAugment and Disout are used for further performance boosting. Experimental results demonstrate that our DD-CNN can learn discriminative acoustic characteristics from audio fragments and effectively reduce the network complexity. Our DD-CNN was used for the low-complexity acoustic scene classification task of the DCASE2020 Challenge, which achieves 92.04% accuracy on the validation set.