ISOLATED WORD SPEECH RECOGNITION SYSTEM USING DYNAMIC TIME WARPING

This paper includes a new approach to develop a real time isolated word speech recognition system for humancomputer interaction. The system is a speaker dependent system. The main motive behind developing this system is to recognize a list of words in which the speaker says through the microphone. The features used are the melfrequency cepstral coefficients (MFCC) which gives the good discrimination of the speech signal. The Dynamic Programming algorithm is used in the system measures the similarity between the stored template and the test template for the speech recognition which gives the optimal distance. The recognition accuracy obtained for the system is 90.1%. We made a simple list of four words of numbers (count), i.e., One, Two, Three and Four and stored them under certain command names. After that when the particular word was spoken on microphone, the system recognized the word and displayed the respective command name in which it was stored. This system can be used in many areas after a little modification for the specific function, for e.g., to control a robot using simple commands and also in many other applications.