Automatic Speech Recognition System is based on the voice as the research area as a cross-disciplinary. Speech Recognition is the high-tech that allows the machine to turn the speech signal into the text through the process of identification and understanding and also make the function of natural voice communication. It has a very close relationship with acoustics, phonetics, linguistics, information theory, pattern recognition theory and neurobiology disciplinary. Over the past decades, a tremendous amount of research has been done on the use of machine learning for speech application area, especially speech recognition step. However, in the past few years, many research has developed on the deep learning approach for speech related application areas such as speech emotional recognition system, speaker recognition and motor sound classification system. Nowadays, this development of deep learning approach has yielded the better results when compared to the others various applications including speech. Deep learning algorithm have been mostly used to further enhance the capabilities of computers so that it understands what humans can do, which includes speech recognition. . Deep Learning classifier is used in many research areas of speech recognition system and speaker recognition system to improve the accuracy of the system. The extracted features and converted feature images are used as the input of the various Deep learning classifiers to get the higher accuracy for speech recognition system. This paper provides the various result based on the different analysis of different speech recognition process when deep learning become a new popular area of machine learning for speech applications. As the experimental results of the system, the various recognition results of different deep learning classifiers in the recognition step of the speech recognition system.