Study on Feature Subspace of Archetypal Emotions for Speech Emotion Recognition
This work addresses speech emotion recognition, an incremental improvement for applications like human-computer interaction.
The paper tackled the problem of distinguishing emotions in speech by proposing a divide-and-conquer approach that constructs feature subspaces for each emotion pair and uses bi-classifiers with voting, achieving better results than traditional multi-classification methods.
Feature subspace selection is an important part in speech emotion recognition. Most of the studies are devoted to finding a feature subspace for representing all emotions. However, some studies have indicated that the features associated with different emotions are not exactly the same. Hence, traditional methods may fail to distinguish some of the emotions with just one global feature subspace. In this work, we propose a new divide and conquer idea to solve the problem. First, the feature subspaces are constructed for all the combinations of every two different emotions (emotion-pair). Bi-classifiers are then trained on these feature subspaces respectively. The final emotion recognition result is derived by the voting and competition method. Experimental results demonstrate that the proposed method can get better results than the traditional multi-classification method.