AINeutralarXiv – CS AI · 5h ago6/10
🧠
Geometric Second-Order Feature Correlation Learning for Self-Supervised Speech Emotion Recognition
Researchers propose a Second-Order Correlation (SOC) layer that improves speech emotion recognition by modeling feature correlations as covariance descriptors rather than treating features independently. Using Log-Euclidean mapping to preserve geometric properties, the method demonstrates superior performance on standard emotion recognition datasets compared to conventional first-order aggregation approaches.