Summary

This chapter attempts to highlight certain uses of Kinect SDK Audio APIs and leverage the Microsoft SAPI to build the speech-enabled application. Before delving into any code, we have purposefully harped on about the basics of the speech recognition system and how it works, so that you feel at ease while running the codes. To aid the understanding process we have also provided a well sketched schematic diagram. You have learned how to create your own grammar either by using code or loading from an XML file and finally learned how to load the grammar into the speech recognizer. We have also shown how to create different grammar builders and load them into the speech recognizer one by one. This helps in increasing the versatility of the command set. Finally the chapter ends with a really cool demo to make the contents of the chapter crystal clear to you.

In the next chapter, we will learn about gesture recognition using a Kinect device.