Speech Emotion Recognition System Based on BP Neural Network in Matlab Environment

Authors:
Guobao Zhang;Qinghua Song;Shumin Fei
Affiliations:
School of Automation, Southeast University, Nanjing, P.R. China 210096;School of Automation, Southeast University, Nanjing, P.R. China 210096;School of Automation, Southeast University, Nanjing, P.R. China 210096
Venue:
ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks, Part II
Year:
2008

Citing 3
Cited 0

2005 Special Issue: Emotion recognition in human-computer interaction

Neural Networks - Special issue: Emotion and brain
Classification of acoustic events using SVM-based clustering schemes

Pattern Recognition
Applying an analysis of acted vocal emotions to improve the simulation of synthetic speech

Computer Speech and Language

Quantified Score

Hi-index	0.00

Visualization

Abstract

An emotion recognition system based on BP neural network to recognize special human affective states existed in the speech signal is presented in this paper. About 600 short sentences with different contents in different emotional speeches from 4 speakers are collected for training and testing the feasibility of the system. The energy, pitch and speech rate characteristics are extracted from these speech signals. angry, calm, happy, sad, and surprise as the 5 typical emotions are classified with BP Neural network. In order to update automatically the emotion recognition system with time, an additional study step, just as the feed-back control, is adopted to train the finished network again according to the output. The experiments show that the system is of satisfactory emotion detection performance for some emotions.