Summary

Exploring the audio capabilities of the Kinect sensor is the essence of this chapter. In order to fully grasp the expanse of the auditory abilities of this novel device, it is essential for us to have an understanding of the underlying hardware and how it functions. Hence, we have delved deep into the functioning of the Kinect microphone array and the need for it. You have learned the reason behind having four microphones and how the design makes the Kinect device a directional audio source detector. You have also learned about all the major terms relating to the Kinect microphone array, such as beamforming, source angle, and beam steering. You have also seen how data is processed in the Kinect audio-processing pipeline. The demo provided demystifies the exact technique of capturing and consequently using the captured audio data. In the next chapter we will raise the bar further by venturing into speech recognition of Kinect audio.