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 |
|
|
|
|
