ERANNs: Efficient Residual Audio Neural Networks for Audio Pattern Recognition

TL;DR

This paper introduces ERANNs, a new CNN architecture for audio pattern recognition that significantly improves inference speed and model size while achieving competitive or state-of-the-art accuracy on multiple audio datasets.

Contribution

The paper proposes ERANNs, a novel CNN architecture that enhances efficiency and performance for APR tasks, with extensive experiments demonstrating its advantages over previous models.

Findings

Achieves 0.450 mAP on AudioSet, slightly below state-of-the-art but with 7.1x faster inference.

Attains state-of-the-art accuracy on ESC-50, UrbanSound8K, and RAVDESS datasets.

ERANNs are 1.7x faster and 2.3x smaller on ESC-50, and 3.3x smaller on RAVDESS.

Abstract

Audio pattern recognition (APR) is an important research topic and can be applied to several fields related to our lives. Therefore, accurate and efficient APR systems need to be developed as they are useful in real applications. In this paper, we propose a new convolutional neural network (CNN) architecture and a method for improving the inference speed of CNN-based systems for APR tasks. Moreover, using the proposed method, we can improve the performance of our systems, as confirmed in experiments conducted on four audio datasets. In addition, we investigate the impact of data augmentation techniques and transfer learning on the performance of our systems. Our best system achieves a mean average precision (mAP) of 0.450 on the AudioSet dataset. Although this value is less than that of the state-of-the-art system, the proposed system is 7.1x faster and 9.7x smaller. On the ESC-50, UrbanSound8K, and RAVDESS datasets, we obtain state-of-the-art results with accuracies of 0.961, 0.908, and 0.748, respectively. Our system for the ESC-50 dataset is 1.7x faster and 2.3x smaller than the previous best system. For the RAVDESS dataset, our system is 3.3x smaller than the previous best system. We name our systems "Efficient Residual Audio Neural Networks".