Automatic recognition of musical patterns plays a crucial part in Musicological research and can become an indispensable tool for the search and comparison of music extracts within a large multimedia database. In today’s life musical band performer requires conductor for the musical performance. Based on this study we present an efficient way for recognition isolated musical patterns in a monophonic environment, using of Dynamic Time Warping a probabilistic framework.In this automatic recognize hand gestures pattern for the musical performance by using the RGB-D Camera. Each pattern, to be recognized, is converted into a sequence of frequency jumps by means of a Dynamic Time Warping. The important Characteristic of Context Dependent Dynamic Time Warping is that it exploits the correlation without using local point. Other is context of Traditional Music, which exhibits certain characteristics that make the classification task easy and accuracy is evaluated over the existing approaches.