Tracking audio sources

The Kinect sensor captures sounds from every direction. Having said that, the audio capture hardware has a specified area (as an imaginary cone) from where it is able to capture audio signals the best. Audio waves that propagate through the length of the cone can be separated from the audio waves that travel across the cone.

Quite often we may find ourselves to be in noisy environments where different background noises and irrelevant sounds could corrupt the quality of our audio stream data analysis and/or the speech recognition. In this type of scenario we can improve the outcome of our application by pointing the cone in the direction of the audio that our application is most interested in capturing. In fact, we can improve the ability to capture and separate that audio source from other competing/distracting audio sources.

The Kinect sensor provides a few APIs for managing the audio source beam angle as well as the sound source angle. Using those APIs, we can set...