MU Digital Repository
Logo

Speech emotion recognition system using both spectral and prosodic features

Augustine, Nevin and Srinivasan, C R and Richards, Kevin (2015) Speech emotion recognition system using both spectral and prosodic features. In: Advances in Electrical, Power Control, Electronics and, 6th and 7th June, 2015, Jawaharlal Nehru University.

[img] PDF
paper.pdf - Published Version
Restricted to Registered users only

Download (326kB) | Request a copy

Abstract

In this paper, we propose an emotion recognition system from speech signal using both spectral and prosodic features. Most traditional systems have focused on spectral features or prosodic features. Since both the spectral and the prosodic features contain emotion information, it is believed that combining spectral features and prosodic features will improve the performance of the emotion recognition system. Therefore, we propose to use both spectral and prosodic features. For spectral features, a GMM super vector based SVM is applied. For prosodic features, a set of prosodic features that are clearly correlated with speech emotional states and SVM is also used for emotion recognition. The combination of both spectral features and prosodic features is done and an SVM is trained using the combined feature vector. The emotion recognition accuracy of our experiments allow us to explain which features carry the most emotional information and why. It also allows us to develop criteria to class emotions together. Using these techniques we achieved high emotion recognition accuracy

Item Type: Conference or Workshop Item (Paper)
Subjects: Engineering > MIT Manipal > Electronics and Communication
Depositing User: MIT Library
Date Deposited: 20 Jan 2016 14:00
Last Modified: 20 Jan 2016 14:00
URI: http://eprints.manipal.edu/id/eprint/145117

Actions (login required)

View Item View Item