A Study of Language and Classifier-independent Feature Analysis for Vocal Emotion Recognition
This work addresses the challenge of cross-language and classifier-agnostic emotion recognition in speech, representing an incremental improvement in feature selection for this domain.
The paper tackles the problem of vocal emotion recognition by proposing an algorithm to extract features that are independent of spoken language and classification method, achieving better performance than state-of-the-art filter methods in many cases.
Every speech signal carries implicit information about the emotions, which can be extracted by speech processing methods. In this paper, we propose an algorithm for extracting features that are independent from the spoken language and the classification method to have comparatively good recognition performance on different languages independent from the employed classification methods. The proposed algorithm is composed of three stages. In the first stage, we propose a feature ranking method analyzing the state-of-the-art voice quality features. In the second stage, we propose a method for finding the subset of the common features for each language and classifier. In the third stage, we compare our approach with the recognition rate of the state-of-the-art filter methods. We use three databases with different languages, namely, Polish, Serbian and English. Also three different classifiers, namely, nearest neighbour, support vector machine and gradient descent neural network, are employed. It is shown that our method for selecting the most significant language-independent and method-independent features in many cases outperforms state-of-the-art filter methods.