E-PANNs: Sound Recognition Using Efficient Pre-trained Audio Neural Networks

TL;DR

This paper introduces E-PANNs, an optimized version of pre-trained audio neural networks that reduces computational and memory demands by 36% and 70% respectively, while slightly improving sound recognition accuracy.

Contribution

The paper presents a pruning-based method to significantly reduce the complexity and size of PANNs, enabling deployment on resource-constrained devices with improved performance.

Findings

E-PANNs requires 36% less computation.

E-PANNs uses 70% less memory.

E-PANNs slightly outperforms original PANNs in sound recognition.

Abstract

Sounds carry an abundance of information about activities and events in our everyday environment, such as traffic noise, road works, music, or people talking. Recent machine learning methods, such as convolutional neural networks (CNNs), have been shown to be able to automatically recognize sound activities, a task known as audio tagging. One such method, pre-trained audio neural networks (PANNs), provides a neural network which has been pre-trained on over 500 sound classes from the publicly available AudioSet dataset, and can be used as a baseline or starting point for other tasks. However, the existing PANNs model has a high computational complexity and large storage requirement. This could limit the potential for deploying PANNs on resource-constrained devices, such as on-the-edge sound sensors, and could lead to high energy consumption if many such devices were deployed. In this paper, we reduce the computational complexity and memory requirement of the PANNs model by taking a pruning approach to eliminate redundant parameters from the PANNs model. The resulting Efficient PANNs (E-PANNs) model, which requires 36\% less computations and 70\% less memory, also slightly improves the sound recognition (audio tagging) performance. The code for the E-PANNs model has been released under an open source license.