Design of an Urdu speech recognizer based upon acoustic phonetic modeling approach

Automatic speech recognition (ASR) is one of the most developing fields of the modern science. It has many important applications in our social life as well as many areas of scientific disciplines like computer science, and media. The main aim of this paper is to analyze and implement different techniques of speech recognition like pattern-matching or acoustic phonetic modeling to Urdu language. A prototype has been developed which recognizes the continuous Urdu speech with 55 to 60% accuracy.