Decision tree SVM model with Fisher feature selection for speech emotion recognition

Linhui Sun,Sheng Fu,Fu Wang

doi:10.1186/s13636-018-0145-5

Abstract

The overall recognition rate will reduce due to the increase of emotional confusion in multiple speech emotion recognition. To solve the problem, we propose a speech emotion recognition method based on the decision tree support vector machine (SVM) model with Fisher feature selection. At the stage of feature selection, Fisher criterion is used to filter out the feature parameters of higher distinguish ability. At the emotion classification stage, an algorithm is proposed to determine the structure of decision tree. The decision tree SVM can realize the two-step classification of the first rough classification and the fine classification. Thus the redundant parameters are eliminated and the performance of emotion recognition is improved. In this method, the decision tree SVM framework is firstly established by calculating the confusion degree of emotion, and then the features with higher distinguish ability are selected for each SVM of the decision tree according to Fisher criterion. Finally, speech emotion recognition is realized based on this model. The decision tree SVM with Fisher feature selection on CASIA Chinese emotion speech corpus and Berlin speech corpus are constructed to validate the effectiveness of our framework. The experimental results show that the average emotion recognition rate based on the proposed method is 9% higher than traditional SVM classification method on CASIA, and 8.26% higher on Berlin speech corpus. It is verified that the proposed method can effectively reduce the emotional confusion and improve the emotion recognition rate.

Highlights

In recent years, speech emotion recognition has been widely applied in the field of human-computer interaction [1,2,3]
The contributions made in this paper include (1) adopt Fisher criterion to remove the redundant features to improve emotion recognition performance; (2) propose an algorithm to determine the structure of decision tree dynamically, and construct the system frameworks on the CASIA Chinese speech emotion corpus and the EMO-DB Berlin speech corpus; and (3) combine Fisher criterion with decision tree support vector machine (SVM), and adopt genetic algorithm to optimize the parameters of SVM to further improve the emotion recognition rate
2.4 Feature selection strategy for decision tree SVM In order to improve the recognition rate of multiple classification speech emotion recognition, we propose a speech emotion recognition method based on the decision tree SVM model and Fisher feature selection

Summary

Introduction

Speech emotion recognition has been widely applied in the field of human-computer interaction [1,2,3]. For each of decision tree SVM, we filter out the feature parameters of higher distinguish ability by Fisher criterion to gain an optimal feature set This model is used for speech emotion recognition. The contributions made in this paper include (1) adopt Fisher criterion to remove the redundant features to improve emotion recognition performance; (2) propose an algorithm to determine the structure of decision tree dynamically, and construct the system frameworks on the CASIA Chinese speech emotion corpus and the EMO-DB Berlin speech corpus; and (3) combine Fisher criterion with decision tree SVM, and adopt genetic algorithm to optimize the parameters of SVM to further improve the emotion recognition rate.

Decision tree SVM model with Fisher feature selection

Methods

Conclusion

Findings

Availability of data and materials Not applicable