This paper introduces different pre-processing classification models and their performance in the Automatic Speech Recognition system. Other Recurrent Neural Network (RNN) architectures have been tested for this problem, such as RNN cells (RNN), bidirectional RNN (BRNN), Long Short-Term Memory (LSTM), and bidirectional LSTM. Mainly, two features have been considered. First, Mel Frequency Cepstral Coefficient (MFCC) plus delta and delta-delta coefficients (39 parameters) have been used. Second, MFCC quantization using Vector Quantization technique has been used as features. All models have been trained on TIMIT database. Vowels, nasals, fricatives, plosives, and silences have been chosen as syllable classes for classification. Experiment results show that BRNN-MFCC-5-{30,30,20,25,25} system give the highest accuracy. It achieved 92.6%. In similar work of using RNN in classification, 83% accuracy was achieved by [1], and 95% had been achieved by [2]. It is also noticeable that the results obtained by using HMM in a similar problem are 80% by[19] and 81.01% by [17].