Music Genre Classification using Large Language Models

TL;DR

This paper explores the use of large language models and transformer architectures for music genre classification, demonstrating that models like AST achieve high accuracy even in zero-shot scenarios.

Contribution

It introduces a novel approach combining LLMs with audio processing for genre classification and compares various models, highlighting the superior performance of transformer-based architectures.

Findings

AST model achieves 85.5% accuracy

Transformer-based models outperform CNNs and traditional methods

Zero-shot classification capability demonstrated

Abstract

This paper exploits the zero-shot capabilities of pre-trained large language models (LLMs) for music genre classification. The proposed approach splits audio signals into 20 ms chunks and processes them through convolutional feature encoders, a transformer encoder, and additional layers for coding audio units and generating feature vectors. The extracted feature vectors are used to train a classification head. During inference, predictions on individual chunks are aggregated for a final genre classification. We conducted a comprehensive comparison of LLMs, including WavLM, HuBERT, and wav2vec 2.0, with traditional deep learning architectures like 1D and 2D convolutional neural networks (CNNs) and the audio spectrogram transformer (AST). Our findings demonstrate the superior performance of the AST model, achieving an overall accuracy of 85.5%, surpassing all other models evaluated. These results highlight the potential of LLMs and transformer-based architectures for advancing music information retrieval tasks, even in zero-shot scenarios.