Speech Emotion Classification with Deep Learning

Deep neural networks have been applied to speech emotion recognition. • Employed for automatic feature extraction from the audio signal in the related field. • Audio signals are essential to have the pre-processing step. • Quality of voice has a direct influence on the speech emotion recognition results. • Acoustic speech features. • Word, phoneme, phrase. • Spectral features. • Mel-frequency Cepstral Coefficients (MFCC)