# Sub-Spectrogram Segmentation for Environmental Sound Classification via Convolutional Recurrent Neural Network and Score Level Fusion

## TL;DR

This paper introduces a novel subspectrogram segmentation approach combined with a CRNN and score level fusion to enhance environmental sound classification accuracy, achieving significant improvements on a public dataset.

## Contribution

The paper proposes a new subspectrogram segmentation method and integrates it with CRNN and score fusion, significantly improving ESC accuracy over traditional methods.

## Key findings

- Achieved 81.9% accuracy on ESC-50 dataset
- Outperformed baseline schemes by 9.1%
- Optimized sub-spectrogram segmentation parameters

## Abstract

Environmental Sound Classification (ESC) is an important and challenging problem, and feature representation is a critical and even decisive factor in ESC. Feature representation ability directly affects the accuracy of sound classification. Therefore, the ESC performance is heavily dependent on the effectiveness of representative features extracted from the environmental sounds. In this paper, we propose a subspectrogram segmentation based ESC classification framework. In addition, we adopt the proposed Convolutional Recurrent Neural Network (CRNN) and score level fusion to jointly improve the classification accuracy. Extensive truncation schemes are evaluated to find the optimal number and the corresponding band ranges of sub-spectrograms. Based on the numerical experiments, the proposed framework can achieve 81.9% ESC classification accuracy on the public dataset ESC-50, which provides 9.1% accuracy improvement over traditional baseline schemes.