Emotional speech recognition aims at classifying the human emotional states viz. happy, neutral, anger and sad etc.,. To classify these emotions we need to extract reliable Acoustic features like prosody and spectral. The time domain features are much less accurate than frequency domain features. So in this paper Mel Frequency Cepstral Coefficients(MFCC) are extracted from Berlin emotional speech corpus and are classified using Class Dependent and Class Independent Linear Discriminant Analysis(CD-LDA and CI-LDA). The results obtained shows the performance variation of the classifiers with respect to the emotional states.