A Study on Broadcast Networks for Music Genre Classification
This addresses the need for compact and generalizable models in music streaming and recommender services, though it appears incremental as it builds on existing broadcast network concepts.
The paper tackled the problem of inefficient temporal feature encoding in convolutional-based music genre classification by studying broadcast-based neural networks, achieving state-of-the-art classification accuracies on datasets like GTZAN, Extended Ballroom, HOMBURG, and FMA with about 180k parameters.
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.