EAViT: External Attention Vision Transformer for Audio Classification

TL;DR

This paper introduces EAViT, a novel external attention vision transformer model that significantly improves audio classification accuracy by capturing long-range dependencies with learnable memory units, outperforming existing methods.

Contribution

The paper proposes the EAViT model, integrating multi-head external attention into Vision Transformer for enhanced audio classification performance.

Findings

EAViT achieves 93.99% accuracy on GTZAN dataset.

External attention improves long-range dependency modeling.

Outperforms state-of-the-art audio classification models.

Abstract

This paper presents the External Attention Vision Transformer (EAViT) model, a novel approach designed to enhance audio classification accuracy. As digital audio resources proliferate, the demand for precise and efficient audio classification systems has intensified, driven by the need for improved recommendation systems and user personalization in various applications, including music streaming platforms and environmental sound recognition. Accurate audio classification is crucial for organizing vast audio libraries into coherent categories, enabling users to find and interact with their preferred audio content more effectively. In this study, we utilize the GTZAN dataset, which comprises 1,000 music excerpts spanning ten diverse genres. Each 30-second audio clip is segmented into 3-second excerpts to enhance dataset robustness and mitigate overfitting risks, allowing for more granular feature analysis. The EAViT model integrates multi-head external attention (MEA) mechanisms into the Vision Transformer (ViT) framework, effectively capturing long-range dependencies and potential correlations between samples. This external attention (EA) mechanism employs learnable memory units that enhance the network's capacity to process complex audio features efficiently. The study demonstrates that EAViT achieves a remarkable overall accuracy of 93.99%, surpassing state-of-the-art models.