Abstract:

The paper presents speech emotion recognition from speech signals based on features analysis and NN-classifier. Automatic Speech Emotion Recognition (SER) is importantfor measuring people's emotions in HCI systems. Ithas dominated psychology by linking expressions to basic emotions (i.e., anger, disgust, fear, happiness, sadness, and surprise). The recognition system involves speech emotion detection, features extraction and selection, and classification. These features help distinguish the maximum number of samples accurately, and the PNN classifier based on discriminate analysis is used to classify the six different expressions. The simulated results will show that the filter-based feature extraction with the used classifier gives much better accuracy with lesser algorithmic complexity than other speech emotion expression recognition approaches

Description:

MLP-Classifier, MFCC, Model, Neural Networks, Prediction