A Study of Language and Classifier-independent Feature Analysis for Vocal Emotion Recognition

TL;DR

This paper introduces a novel feature selection algorithm for vocal emotion recognition that is independent of language and classifier, demonstrating improved performance across multiple languages and classifiers.

Contribution

The paper presents a three-stage algorithm for extracting language- and classifier-independent features, outperforming existing filter methods in vocal emotion recognition.

Findings

The proposed method achieves higher recognition rates than state-of-the-art filter methods.

It is effective across multiple languages including Polish, Serbian, and English.

The approach works well with various classifiers such as SVM, neural networks, and nearest neighbor.

Abstract

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.