High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

Speech Emotion Recognition using SVM Algorithm

Author(s):

Jyoti , GJU S&T,HISAR; Dr. Sanjeev Dhull, GJU S&T,HISAR

Keywords:

SVM, Speech Emotion Recognition, Linear Kernel, Gaussian Radial Basis Function, MFCC

Abstract

Speech Emotion Recognition is a recent research topic in the field of Human Computer Interaction. The objective of this paper is to use Support Vector Machine (SVM) classifier to classify seven different emotions happiness, anger, sadness, boredom, disgust, neutral, fear. The explored features include: pitch, mel-frequency spectrum coefficients (MFCC), Spectro -temporal features, formants and energy measurements. In this paper we use two different kernel: Linear (Homogeneous), Gaussian radial basis function kernel to get higher accuracy for emotion recognition in speech .Performance analysis is done by using the confusion matrix and the accuracy obtained is 95% on the basis of data set. Finally results for different combination of the features and on different databases are compared and we get SVM recognition accuracy is more than other algorithm.

Other Details

Paper ID: IJSRDV5I60591
Published in: Volume : 5, Issue : 6
Publication Date: 01/09/2017
Page(s): 2099-2103

Article Preview

Download Article