ACHIEVING SECURITY VIA SPEECH RECOGNITION

Speech is one of the essential sources of the conversation between human beings. We as humans speak and listen to each other in human-human interface. People have tried to develop systems that can listen and prepare a speech as persons do so naturally. This paper presents a brief survey on Speech recognition, allow people to compose documents and control their computers with their voice. In other words, the process of enabling a machine (like a computer) to identify and respond to the sounds produced in human speech. ASR can be treated as the independent, computer-driven script of spoken language into readable text in real time. The Speech Recognition system requires careful attention to the following issues: Meaning of various types of speeches, speech representation, feature extraction techniques, speech classifiers, and database and performance evaluation. This paper helps in understanding the technique along with their pros and cons. A comparative study of different technique is done as per stages.