Speech recognition is a vast research field for researchers in modern era. Earlier, the human language was processed by the computer system for speech recognition. Thus, the main objective is to develop recognition system which improves human to human communication by enabling human-machine communication by processing of text or speech by a module named pyaudio. Various applications of speech recognition systems are present and these all includes various research challenges. A critical machine learning based review is defined which addresses the various challenging tasks of speech recognition system. In the existing systems, the recognition rate is very less and the noise ration during the recognition process creates a problem. Thus in this project we try to address such kind of challenges and provides a solution to work further in future.