Impact of temporal resolution on convolutional recurrent networks for audio tagging and sound event detection

TL;DR

This paper investigates how varying the temporal resolution in convolutional recurrent neural networks affects their performance in audio tagging and sound event detection, providing insights for optimizing design choices.

Contribution

It offers a comprehensive analysis of the impact of temporal resolution adjustments on neural network performance across different sound recognition scenarios.

Findings

Optimal temporal resolution varies with recognition scenario

Adjusting pooling operations significantly influences localization accuracy

Performance improvements depend on specific evaluation metrics

Abstract

Many state-of-the-art systems for audio tagging and sound event detection employ convolutional recurrent neural architectures. Typically, they are trained in a mean teacher setting to deal with the heterogeneous annotation of the available data. In this work, we present a thorough analysis of how changing the temporal resolution of these convolutional recurrent neural networks - which can be done by simply adapting their pooling operations - impacts their performance. By using a variety of evaluation metrics, we investigate the effects of adapting this design parameter under several sound recognition scenarios involving different needs in terms of temporal localization.