Multi-scale modulation filtering in automatic detection of emotions in telephone speech

This study investigates emotion detection from noise-corrupted telephone speech. A generic modulation filtering approach for audio pattern recognition is proposed that utilizes inherent long-term properties of acoustic features in different classes. When applied to binary classification along the activation and valence dimensions, filtering the baseline short-time timbral features in both the training and detection phase leads to significant improvement especially in noise robustness. Automatic selection of training data based on the filter´s prediction residual further improves the results.