# Semi-Supervised Self-Learning Enhanced Music Emotion Recognition

arXiv: https://arxiv.org/abs/2410.21897 · HTML: https://mlsanity.com/paper/2410.21897/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 23 references that are in the map.
- First posted on arXiv 29 Oct 2024.

## Builds on (most cited first, 10 of 10)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Unsupervised Label Noise Modeling and Loss Correction](https://mlsanity.com/paper/1904.11238/) (2019)
- [Joint Optimization Framework for Learning with Noisy Labels](https://mlsanity.com/paper/1803.11364/) (2018)
- [R-Drop: Regularized Dropout for Neural Networks](https://mlsanity.com/paper/2106.14448/) (2021)
- [Comparison and Analysis of Deep Audio Embeddings for Music Emotion Recognition](https://mlsanity.com/paper/2104.06517/) (2021)
- [Music Mood Detection Based On Audio And Lyrics With Deep Neural Net](https://mlsanity.com/paper/1809.07276/) (2018)
- [Singer Identification Using Deep Timbre Feature Learning with KNN-Net](https://mlsanity.com/paper/2102.10236/) (2021)
- [User independent Emotion Recognition with Residual Signal-Image Network](https://mlsanity.com/paper/1908.03692/) (2019)
- [Investigation of Singing Voice Separation for Singing Voice Detection in Polyphonic Music](https://mlsanity.com/paper/2004.04040/) (2020)

## Abstract (arXiv)

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.