Device-Robust Acoustic Scene Classification Based on Two-Stage Categorization and Data Augmentation

TL;DR

This paper introduces a two-stage CNN-based system with data augmentation for device-robust acoustic scene classification, achieving high accuracy on DCASE 2020 Challenge tasks.

Contribution

It proposes a novel two-stage classification approach combined with data augmentation and model quantization for improved device-robust acoustic scene classification.

Findings

Achieved 76.9% accuracy on Task 1a with data augmentation.

Attained 81.9% accuracy through model fusion.

Reached 96.7% accuracy on Task 1b with a compact model.

Abstract

In this technical report, we present a joint effort of four groups, namely GT, USTC, Tencent, and UKE, to tackle Task 1 - Acoustic Scene Classification (ASC) in the DCASE 2020 Challenge. Task 1 comprises two different sub-tasks: (i) Task 1a focuses on ASC of audio signals recorded with multiple (real and simulated) devices into ten different fine-grained classes, and (ii) Task 1b concerns with classification of data into three higher-level classes using low-complexity solutions. For Task 1a, we propose a novel two-stage ASC system leveraging upon ad-hoc score combination of two convolutional neural networks (CNNs), classifying the acoustic input according to three classes, and then ten classes, respectively. Four different CNN-based architectures are explored to implement the two-stage classifiers, and several data augmentation techniques are also investigated. For Task 1b, we leverage upon a quantization method to reduce the complexity of two of our top-accuracy three-classes CNN-based architectures. On Task 1a development data set, an ASC accuracy of 76.9\% is attained using our best single classifier and data augmentation. An accuracy of 81.9\% is then attained by a final model fusion of our two-stage ASC classifiers. On Task 1b development data set, we achieve an accuracy of 96.7\% with a model size smaller than 500KB. Code is available: https://github.com/MihawkHu/DCASE2020_task1.