Low-complexity deep learning frameworks for acoustic scene classification

TL;DR

This paper introduces low-complexity deep learning frameworks for acoustic scene classification that utilize spectrogram transformations, data augmentation, and classifier fusion, achieving significant accuracy improvements on a standard dataset.

Contribution

The work presents a novel low-complexity framework combining multiple spectrogram-based classifiers and fusion techniques for improved acoustic scene classification.

Findings

Achieved 60.1% accuracy on DCASE 2022 dataset.

Improved baseline accuracy by 17.2%.

Demonstrated effectiveness of spectrogram fusion and data augmentation.

Abstract

In this report, we presents low-complexity deep learning frameworks for acoustic scene classification (ASC). The proposed frameworks can be separated into four main steps: Front-end spectrogram extraction, online data augmentation, back-end classification, and late fusion of predicted probabilities. In particular, we initially transform audio recordings into Mel, Gammatone, and CQT spectrograms. Next, data augmentation methods of Random Cropping, Specaugment, and Mixup are then applied to generate augmented spectrograms before being fed into deep learning based classifiers. Finally, to achieve the best performance, we fuse probabilities which obtained from three individual classifiers, which are independently-trained with three type of spectrograms. Our experiments conducted on DCASE 2022 Task 1 Development dataset have fullfiled the requirement of low-complexity and achieved the best classification accuracy of 60.1%, improving DCASE baseline by 17.2%.