Dynamic time Warping using MATLAB & PRAAT

The Voice is a signal of infinite information. Digital processing of speech signal is very important for high and precise automatic voice recognition technology. Speech recognition has found its application on various aspects of our daily lives from automatic phone answering service to dictating text and issuing voice commands to computers. We focus mainly on two points 1. The pre-processing stage that extracts salient features of a speech signal and a technique called Dynamic Time Warping commonly used to compare the feature vectors of speech signals. These techniques are applied for recognition of isolated as well as connected spoken words. 2. In this case the experiment is conducted in MATLAB & PRAAT to verify these techniques. Using the Matlab statistical difference between two wave signals are calculated. & using PRAAT two wave signals are aligned. Statistical difference obtained by these two ways is noticeable i.e. using MATLAB average distance is calculated which is 3.2843 & using PRAAT average distance is calculated which is 0.002235.