Automated computer speech detection has been a goal of research for almost four decades. The idea underlying the development of a voice recognition system is that it is beneficial for people to communicate with a computer, robot or another device via speech. Researchers want to utilize people's voices in an integrated environment to provide customers comfort and flexibility in today's era. Speech recognition is dependent on the input voice signal. It enables the computer to transform the voice signal to text or instructions using the technique of recognition and understanding. This article describes the fundamental concept of speaking recognition, types of voice recognition, difficulties with speech recognition, several ways to gather characteristics, and different pattern-matching algorithms to identify the different speakers. The technology of voice recognition is inspired by a wide vocabulary automated speech recognition system which allows language-independent operation and continuous speaking in a foreign language.