Low-Complexity Acoustic Scene Classification Using Parallel Attention-Convolution Network

TL;DR

This paper introduces a low-complexity acoustic scene classification system using a parallel attention-convolution network, achieving state-of-the-art accuracy with minimal computational resources, suitable for real-time applications.

Contribution

The paper presents a novel parallel attention-convolution network architecture combined with techniques like knowledge distillation and data augmentation for efficient acoustic scene classification.

Findings

Achieved 56.10% accuracy on DCASE2023 dataset.

Parameter count of 5.21K with 1.44 million MACs.

Outperformed top systems in accuracy and complexity.

Abstract

This work is an improved system that we submitted to task 1 of DCASE2023 challenge. We propose a method of low-complexity acoustic scene classification by a parallel attention-convolution network which consists of four modules, including pre-processing, fusion, global and local contextual information extraction. The proposed network is computationally efficient to capture global and local contextual information from each audio clip. In addition, we integrate other techniques into our method, such as knowledge distillation, data augmentation, and adaptive residual normalization. When evaluated on the official dataset of DCASE2023 challenge, our method obtains the highest accuracy of 56.10% with parameter number of 5.21 kilo and multiply-accumulate operations of 1.44 million. It exceeds the top two systems of DCASE2023 challenge in accuracy and complexity, and obtains state-of-the-art result. Code is at: https://github.com/Jessytan/Low-complexity-ASC.