This study proposes an effective angry speech detection approach employing the TEO-based feature extraction. Decorrelation processing is applied to the TEO-based feature to increase model training ability by decreasing the correlation between feature elements and vector size. Minimum classification error training is employed to increase the discrimination between the angry speech model and other stressed speech models. Combination with the conventional Mel frequency cepstral coefficients (MFCC) is also employed to leverage the effectiveness of MFCC to characterize the spectral envelope of speech signals. Experimental results over the SUSAS corpus demonstrate the proposed angry speech detection scheme is effective at increasing detection accuracy on an open-speaker and open-vocabulary task. An improvement of up to 7.78% in classification accuracy is obtained by combination of the proposed methods including decorrelation of TEO-based feature vector, discriminative training, and classifier combination.
Bibliographic reference. Kim, Wooil / Hansen, John H. L. (2009): "Robust angry speech detection employing a TEO-based discriminative classifier combination", In INTERSPEECH-2009, 2019-2022.