A Study on Broadcast Networks for Music Genre Classification

TL;DR

This paper explores broadcast neural networks for music genre classification, aiming to improve temporal feature localization and generalization with a compact model, achieving state-of-the-art results on multiple datasets.

Contribution

It introduces and evaluates twelve variants of broadcast networks tailored for music genre classification, emphasizing their effectiveness and efficiency.

Findings

Achieved state-of-the-art accuracy on GTZAN, Ballroom, HOMBURG, and FMA datasets.

Demonstrated the effectiveness of broadcast networks in encoding temporal features.

Provided insights into network configuration impacts on classification performance.

Abstract

Due to the increased demand for music streaming/recommender services and the recent developments of music information retrieval frameworks, Music Genre Classification (MGC) has attracted the community's attention. However, convolutional-based approaches are known to lack the ability to efficiently encode and localize temporal features. In this paper, we study the broadcast-based neural networks aiming to improve the localization and generalizability under a small set of parameters (about 180k) and investigate twelve variants of broadcast networks discussing the effect of block configuration, pooling method, activation function, normalization mechanism, label smoothing, channel interdependency, LSTM block inclusion, and variants of inception schemes. Our computational experiments using relevant datasets such as GTZAN, Extended Ballroom, HOMBURG, and Free Music Archive (FMA) show state-of-the-art classification accuracies in Music Genre Classification. Our approach offers insights and the potential to enable compact and generalizable broadcast networks for music and audio classification.