Studying the Effect of Audio Filters in Pre-Trained Models for Environmental Sound Classification

TL;DR

This paper introduces a two-level classification approach for environmental sound recognition, incorporating various audio filters including a novel Audio Crop method, achieving high accuracy on the ESC-50 dataset.

Contribution

It proposes a new two-level classification methodology and introduces a novel Audio Crop filter that improves sound classification accuracy.

Findings

Maximum accuracy of 78.75% in Level 1 classification

Maximum accuracy of 98.04% in Level 2 classification

Audio Crop filter outperforms other filters in most cases

Abstract

Environmental Sound Classification is an important problem of sound recognition and is more complicated than speech recognition problems as environmental sounds are not well structured with respect to time and frequency. Researchers have used various CNN models to learn audio features from different audio features like log mel spectrograms, gammatone spectral coefficients, mel-frequency spectral coefficients, generated from the audio files, over the past years. In this paper, we propose a new methodology : Two-Level Classification; the Level 1 Classifier will be responsible to classify the audio signal into a broader class and the Level 2 Classifiers will be responsible to find the actual class to which the audio belongs, based on the output of the Level 1 Classifier. We have also shown the effects of different audio filters, among which a new method of Audio Crop is introduced in this paper, which gave the highest accuracies in most of the cases. We have used the ESC-50 dataset for our experiment and obtained a maximum accuracy of 78.75% in case of Level 1 Classification and 98.04% in case of Level 2 Classifications.