Improving Deep Learning Sound Events Classifiers using Gram Matrix Feature-wise Correlations

TL;DR

This paper introduces a novel sound event classification method that leverages Gram matrix-based feature correlations from CNN activations, improving accuracy across multiple architectures and datasets.

Contribution

It presents a new approach using Gram matrices for feature correlation analysis in CNNs, enhancing sound event classification performance.

Findings

Consistent improvement over baseline models across architectures.

Effective application to multiple CNN architectures.

Validated on two different datasets.

Abstract

In this paper, we propose a new Sound Event Classification (SEC) method which is inspired in recent works for out-of-distribution detection. In our method, we analyse all the activations of a generic CNN in order to produce feature representations using Gram Matrices. The similarity metrics are evaluated considering all possible classes, and the final prediction is defined as the class that minimizes the deviation with respect to the features seeing during training. The proposed approach can be applied to any CNN and our experimental evaluation of four different architectures on two datasets demonstrated that our method consistently improves the baseline models.