Automatic detection of anger in telephone speech with robust autoregressive modulation filtering

A new system for automatic detection of angry speech is proposed. Using simulation of far-end-noise-corrupted telephone speech and the widely used Berlin database of emotional speech, autoregressive prediction of features across speech frames is shown to contribute significantly to both the clean speech performance and the robustness of the system. The autoregressive models are learned from the training data in order to capture long-term temporal dynamics of the features. Additionally, linear predictive spectrum analysis outperforms conventional Fourier spectrum analysis in terms of robustness in the computation of mel-frequency cepstral coefficients in the feature extraction stage.