Locally Activated Gated Neural Network for Automatic Music Genre Classification

Automatic music genre classification is a prevailing pattern recognition task, and many algorithms have been proposed for accurate classification. Considering that the genre of music is a very broad concept, even music within the same genre can have significant differences. The current methods have not paid attention to the characteristics of large intra-class differences. This paper presents a novel approach to address this issue, using a locally activated gated neural network (LGNet). By incorporating multiple locally activated multi-layer perceptrons and a gated routing network, LGNet adaptively employs different network layers as multi-learners to learn from music signals with diverse characteristics. Our experimental results demonstrate that LGNet significantly outperforms the existing methods for music genre classification, achieving a superior performance on the filtered GTZAN dataset.

Automated summary

This paper proposes a novel approach, LGNet, to address the issue of large intra-class differences in music genre classification. By incorporating multiple locally activated multi-layer perceptrons and a gated routing network, LGNet adaptively learns from music signals with diverse characteristics. Experimental results demonstrate that LGNet outperforms existing methods, achieving superior performance on the filtered GTZAN dataset.