Stacked Convolutional and Recurrent Neural Networks for Music Emotion Recognition

TL;DR

This paper introduces a combined CNN and RNN approach for music emotion recognition in valence-arousal space, achieving state-of-the-art accuracy with fewer parameters.

Contribution

The proposed model uses a novel CNN-RNN architecture with fewer parameters, improving emotion recognition accuracy on a benchmark dataset.

Findings

Achieved RMSE of 0.202 for arousal

Achieved RMSE of 0.268 for valence

Outperformed previous methods on the dataset

Abstract

This paper studies the emotion recognition from musical tracks in the 2-dimensional valence-arousal (V-A) emotional space. We propose a method based on convolutional (CNN) and recurrent neural networks (RNN), having significantly fewer parameters compared with the state-of-the-art method for the same task. We utilize one CNN layer followed by two branches of RNNs trained separately for arousal and valence. The method was evaluated using the 'MediaEval2015 emotion in music' dataset. We achieved an RMSE of 0.202 for arousal and 0.268 for valence, which is the best result reported on this dataset.