Abstract: Speech has a number of characteristic, the extraction of which can play an important role in the accuracy of speech recognition. In this regard, many researchers have attempted to investigate these features and provide methods which enhance the recognition and identification of speech states. These features include MFCC coefficients, energy, Formant Frequency and Pitch Frequency which are highly important in speech state recognition system. This paper explores the effect of these features on speech state recognition and four different states, i.e. angry, happy, natural and question will be tested. The study investigates a variety of speech characteristics in form of a vector contains 55-characteristics. In the next step, drawing on PSO optimization algorithm, 49, 24 and 15-characteristic vectors are achieved. The less the characteristics of a vector are, the higher the action velocity will be. After that, the mean Normalization, Cepstral variance and Cepstral gain methods are applied on these vectors and using GMM algorithm, speech state recognition is executed on normalized vectors. Finally, following the normalization of the output vectors and speech state recognition through GMM algorithm, the effect of different speech characteristics as well as different normalization methods on speech state recognition are examined.