Semi-Supervised Self-Learning Enhanced Music Emotion Recognition

TL;DR

This paper introduces a semi-supervised self-learning approach for music emotion recognition that effectively handles label noise from segment-based methods, improving performance on limited datasets.

Contribution

The paper proposes a novel semi-supervised self-learning method to mitigate label noise in segment-based music emotion recognition, enhancing accuracy with limited data.

Findings

Achieves better or comparable performance on three public datasets.

Effectively differentiates correct and incorrect labels in segment data.

Improves robustness of emotion recognition models.

Abstract

Music emotion recognition (MER) aims to identify the emotions conveyed in a given musical piece. However, currently, in the field of MER, the available public datasets have limited sample sizes. Recently, segment-based methods for emotion-related tasks have been proposed, which train backbone networks on shorter segments instead of entire audio clips, thereby naturally augmenting training samples without requiring additional resources. Then, the predicted segment-level results are aggregated to obtain the entire song prediction. The most commonly used method is that the segment inherits the label of the clip containing it, but music emotion is not constant during the whole clip. Doing so will introduce label noise and make the training easy to overfit. To handle the noisy label issue, we propose a semi-supervised self-learning (SSSL) method, which can differentiate between samples with correct and incorrect labels in a self-learning manner, thus effectively utilizing the augmented segment-level data. Experiments on three public emotional datasets demonstrate that the proposed method can achieve better or comparable performance.