Emotion Recognition based on audio signal using GFCC Extraction and BPNN Classification

For automatic speech recognition (ASR) there is a big challenge which deals with momentous presentation reduction in high noisy environments. This paper presents our emotion classification based on Gammatone frequency cepstrum coefficient used for feature extraction along with Back propagation neural network and the experimental results on English speech data. Eventually, we obtained significant presentation gains with the new feature in various noise conditions when compared with traditional approaches. In our proposed work we considered two emotions SAD and HAPPY which are used to show the implementation results. The simulation environment taken to implement the whole process is in MATLAB